JP2012043135A - Stream monitoring system and stream monitoring program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a stream monitoring system capable of efficiently detecting and reporting an abnormal stream of a waterway under observation with an economically advantageous configuration.SOLUTION: An image processing part 13 includes: a stream image processing part 15 that captures and quantizes a fluctuation of water from an image of a stream (Wb) part taken by a camera 11 and creates flow rate data that indicates a flow rate of the stream (Wb) of a waterway 1; and a determination processing part 16 that determines whether or not the flow rate of the waterway 1 is in a normal state, that is, within a set range according to a setting parameter using the flow rate data obtained by the stream image processing part 15 as determination object data.

Description

  The present invention relates to a water flow monitoring system and a water flow monitoring program for determining a water flow amount of a water channel based on a time-series image of a water flow portion of the water channel photographed by a monocular camera (one camera).

  Conventionally, as a monitoring means for monitoring the water flow condition of a water channel, monitoring is performed by direct observation of a monitor or visual observation on a monitor screen, or automatic measurement using measuring instruments such as a water flow meter, a water pressure meter, and a flow meter. I came. The visual observation by the supervisor must always have a supervisor, and there is a problem in reliability because there is a risk of overlooking the abnormality of the flowing water amount as well as a heavy human burden. In addition, monitoring by automatic measurement requires that a measuring device be installed in the water channel, which requires a lot of time and labor for installation and maintenance and inspection, and has a problem in terms of economy. Furthermore, in facilities and equipment where there are multiple waterways to be monitored (for example, industrial cooling and drainage equipment and artificial head waterways), the above-mentioned measuring devices must be provided for each waterway, and the problem is more pronounced. It was.

  Conventionally, there has been a debris flow generation prediction device that detects and predicts the occurrence of debris flow in a river by monitoring the flow width, flow velocity, water level, etc. of the river using a monitoring camera as a water channel monitoring technique by the monitor screen of the observer.

JP 2002-208075 A

  As described above, conventionally, in facilities for monitoring the water flow condition of a water channel, it is necessary to equip the water channel to be monitored with a measuring device, so that much time and labor are required for installation and maintenance inspection work. In addition, there was a problem in terms of economy. Furthermore, when there are a plurality of water channels to be monitored, it is necessary to equip each water channel with a measuring device.

  An object of the present invention is to provide a running water monitoring system and a running water monitoring program capable of efficiently detecting and notifying an abnormality in running water of a water channel being monitored with an economically advantageous configuration.

  A water flow monitoring system capable of efficiently detecting and notifying a water flow abnormality in each water channel with a simple system configuration using a monocular camera (one imaging camera) for a plurality of water channels to be monitored, and The purpose is to provide a running water monitoring program.

  Embodiments of the present invention are obtained by a monocular camera that captures an image of a flowing water portion of a water channel, an image processing unit that captures and quantifies water fluctuations from an image of the flowing water image captured by the monocular camera, and the image processing unit. And a determination processing means for determining whether or not the amount of flowing water in the water channel is in a normal state based on a setting parameter using the determined value as determination target data.

  In addition, a monocular camera that photographs the water surface of the water channel from obliquely above, a processing unit that captures and quantifies fluctuations in the water surface from an image of each frame photographed by the camera, and the camera based on the quantized value. Image processing means for specifying the highest position coordinates of fluctuations in the horizontal direction on the frame of the captured image, the highest position coordinates of fluctuations specified by the image processing means, and the set position in the vertical direction on the frame There is provided a water flow monitoring system comprising: a determination unit that determines a water flow amount of the water channel based on a difference from coordinates.

  In addition, a monocular camera that photographs the water surface of the water channel from obliquely above, a processing unit that captures and quantifies fluctuations in the water surface from an image of each frame photographed by the camera, and the camera based on the quantized value. Image processing means for specifying the horizontal coordinate position of the fluctuation width in the vertical setting position on the frame of the photographed image, the positional coordinate of the fluctuation width specified by the image processing means, and the position on the frame There is provided a running water monitoring system comprising: a judging unit that judges a running water amount of the water channel based on a difference from a position coordinate of a set width in a horizontal direction at a set position.

  A water flow monitoring program for causing a computer to function as a water flow monitoring system for monitoring a water flow amount of the water channel based on an image of the water channel photographed by a monocular camera, wherein the image of a water flow portion of the water channel photographed by the camera Provided is a water flow monitoring program that causes a computer to realize an image processing function that captures and quantifies fluctuations in water and a determination processing function that determines the amount of water flowing in the water channel using the value obtained by the image processing function as determination target data .

  According to the embodiment of the present invention, it is possible to efficiently detect and notify an abnormality of flowing water in a water channel that is a monitoring target with an economically advantageous configuration. In addition, it is possible to efficiently detect and notify a water flow abnormality of each water channel for each water channel with a simple system configuration using a monocular camera (one imaging camera) for a plurality of water channels to be monitored.

The block diagram which shows the structure of the flowing water monitoring system which concerns on embodiment of this invention. The figure which shows the example of arrangement | positioning of the camera which images the monitoring object and monitoring object in the said embodiment. The side view which shows the example of arrangement | positioning of the monitoring object and camera shown in the said FIG. The figure which shows an example of the monitoring object area | region division in the image image | photographed with the camera in the said embodiment. The flowchart which shows the process sequence of the flowing water monitoring system which concerns on the said embodiment. The figure for demonstrating the increase / decrease parameter in the flowing water monitoring system of the said embodiment. The figure for demonstrating the excess determination process in the flowing water monitoring system of the said embodiment. The figure which shows the example of arrangement | positioning of the camera which images the monitoring object and the monitoring object in other Embodiment 1 of this invention. The figure which shows the image | video frame for demonstrating the image process (flowing water amount determination process) in embodiment shown in the said FIG. The figure which shows the example of arrangement | positioning (a) of the camera which images the monitoring object and monitoring object in other Embodiment 2 of this invention, and the image | video frame (b) for demonstrating image processing (flowing water amount determination processing). FIG. 2 is a block diagram showing components embodied by the image processing unit shown in FIG. 1. The block diagram which shows the structure of the image process part shown in the said FIG. The figure for demonstrating the variation state determination conditions of the pixel in the congestion detection determination process in the case of detecting the degree of water fluctuation as a congestion degree in the image processing unit shown in FIG. The figure which shows the threshold value fluctuation | variation of the stable pixel in the said congestion detection determination process, a fluctuation | variation pixel, and an excessive fluctuation | variation pixel. The figure for demonstrating the determination processing operation | movement of the block unit in the said congestion detection determination processing. The figure for demonstrating the occupation rate calculation operation | movement of the stable pixel of a block unit in the said congestion detection determination process, a fluctuation | variation pixel, and an excessive fluctuation | variation pixel (fluctuation detection pixel). The figure for demonstrating the final determination process operation | movement of the block unit in the said congestion detection determination process. The figure for demonstrating the final determination process operation | movement of the block unit in the said congestion detection determination process. The figure for demonstrating the final determination process operation | movement of the block unit in the said congestion detection determination process. 7 is a time chart for explaining flow, congestion state determination, release, log (flow / congestion), and image storage processing operations in the congestion detection determination process.

  The flowing water monitoring system according to the embodiment of the present invention captures a flowing water portion of a water channel with a monocular camera, recognizes a variation pixel (a variation pixel set) of the flowing water portion from this image, and detects the variation pixel in the water of the flowing water portion. We catch as fluctuation. This water fluctuation is quantized, and the water flow amount state of the water channel is in a normal flow amount state depending on whether or not the amount of water fluctuation (degree of fluctuation) in the image of the flowing water portion is within a set range. It is determined whether or not. To give a specific example, water that is discharged from a plurality of industrial canals (for example, water flowing through the heads of a plurality of outlets) is simultaneously photographed with a single camera (monocular camera) and cut into discharge units. For each cut-out image, the degree of water fluctuation in the image is recognized and quantized, and the amount of water flowing through each water discharge channel is monitored simultaneously (see FIGS. 1 to 7). As a specific example of image processing for recognizing and quantizing the degree of water fluctuation described above, in this embodiment, the degree of water fluctuation is calculated as a congestion rate, and [increase in congestion rate = increase in the amount of flowing water (of fluctuation) The degree of congestion detection using image processing established by the present applicant is a technology for monitoring the amount of flowing water in a water channel by recognizing that the degree of congestion is small) and the amount of flowing water is decreasing (the degree of fluctuation is small). (See FIGS. 11 to 20).

  Further, as another embodiment, for a water channel including a river, the water channel is photographed with a fixed monocular camera, for example, a bird's-eye view from obliquely above, and the fluctuation of the water surface of the water channel (for example, surface tension wave) is taken from the photographed image. The vertical position coordinates of the horizontal fluctuation (surface tension wave) in the horizontal direction on the screen in units of frames, or the width of fluctuation in the same direction in the same horizontal position on the screen The flow amount of the water channel is estimated from the difference between the obtained position coordinate and the position coordinate set on the screen, and the flow amount of the water channel is monitored (see FIGS. 8 to 10).

  The flowing water amount monitoring mechanism of the above-described embodiment is realized by an image processing technique that recognizes and quantizes the degree of water fluctuation from an image captured by a monocular camera. Therefore, it is possible to efficiently detect and notify an abnormality of the flowing water of the water channel being monitored with an economically advantageous configuration without providing a sensor directly in the flowing water portion of the water channel. In addition, it is possible to efficiently detect and notify a water flow abnormality of each water channel for each water channel with a simple system configuration using a monocular camera (one imaging camera) for a plurality of water channels to be monitored.

  A flowing water monitoring system according to an embodiment of the present invention will be described below with reference to the drawings.

  As shown in FIG. 1, the flowing water monitoring system according to this embodiment includes a monocular camera (one camera) 11 that captures an image of a flowing water (Wb) portion in the water channel 1, and flowing water (Wb) captured by the camera 11. An image that captures water fluctuations from an image of a flowing water (Wb) part captured by the capture unit 12 that captures an image of the part, and determines the amount of flowing water in the water channel 1 based on the information on the fluctuations The processing unit 13 and an output unit 14 that outputs information on the determination result of the image processing unit 13 are provided.

  The camera 11 captures an image of the water channel 1 to be monitored at a certain position and angle of view. In this embodiment, as shown in FIGS. 2 to 4, a plurality of industrial water discharge channels (for example, cooling water discharge channels) are set as monitoring target water channels so that the plurality of water discharge channels can be accommodated in one frame image. An image obtained by photographing the plurality of water discharge channels is output as a frame unit video. 2 shows the configuration of the water channel 1 to be monitored and the positional relationship of the camera 11 with respect to the water channel 1. FIG. 3 is a camera layout view of the water channel viewed obliquely from above. FIG. 3 shows the camera viewed from the side. FIG. 4 is a diagram showing a cut-out image of the water channel 1 photographed by the camera 11.

  In the configuration shown in FIGS. 2 and 3, the flowing water (Wb) portion photographed by the camera 11 is juxtaposed to the water channel 1 to be monitored in order to make the fluctuation (diffuse reflection) of the water incident on the camera 11 more prominent. The plurality of (n) water discharge ports 1d, 1d,..., 1d are illuminated by headlamps 2 at the head portions 1h, 1h,. This illuminating lamp 2 is driven to turn on in synchronization with the processing operation of the image processing unit 13. Here, the discharge water (Wa) flowing through the water channel 1 is distributed to the water outlets 1d, 1d,..., 1d of the m water channels, and the water outlets 1d, 1d,. An example of the process of uniformly discharging the flowing water (Wb) from 1d to the drop portions 1h, 1h,..., 1h to uniformly cool the surface of the member to be cooled (B) is shown.

  The cut-out image shown in FIG. 4 includes each flowing water at the heads 1h, 1h,..., 1h of the m outlets 1d, 1d,. From Wb), an image of the flowing water (Wb) portion is cut out as cut-out images p1, p2,. The image processing unit 13 performs a running water amount determination process for running water (Wb) for each of the cutout images p1, p2,.

  The image processing unit 13 captures and quantizes the fluctuation of water from the image of the flowing water (Wb) portion captured by the camera 11 and generates flowing water amount data indicating the amount of flowing water (Wb) in the water channel 1. Determination processing for determining whether or not the water flow amount of the water channel 1 is in a normal state within the setting range based on the setting parameter using the water flow amount data obtained by the unit 15 and the water flow image processing unit 15 as determination target data Unit 16.

  The running water image processing unit 15 buffers the latest frame unit image captured by the capture unit 12 as a current processing target image (video frame), and water fluctuation from the video frame of the running water (Wb) portion. And determining the flow rate data calculated by the flow rate derivation processing unit 15b by the determination processing unit 16 and calculating the flow rate data indicating the flow rate of the flow (Wb) in the water channel 1 A running water amount buffer 15c that buffers as target data is provided.

  In this embodiment, the flowing water amount derivation processing unit 15b is realized by the congestion rate deriving unit based on the congestion detection technique described above, and hereinafter, the “flowing water amount deriving processing unit” is referred to as a “congestion rate deriving unit”. The “flowing water amount buffer” is referred to as a “congestion rate buffer”.

  In the congestion rate deriving process by the congestion rate deriving unit 15b, as described above, the degree of water fluctuation is calculated as the congestion rate, and [increase in congestion rate = increase in the amount of running water (the degree of fluctuation is large)], [ It is recognized that the congestion rate is reduced = the amount of running water is reduced (the degree of fluctuation is small). More specific configuration and operation of the congestion rate deriving unit 15b will be described later with reference to FIGS.

  The determination processing unit 16 uses the congestion rate stored in the congestion rate buffer 15c of the flowing water image processing unit 15 as determination target data, and determines whether or not the congestion rate has exceeded based on setting parameters described later. The determination result buffer 16b that holds the determination result information (abnormal / normal) of the flow amount increase / decrease determination unit 16a, and the flow amount of the water channel 1 is in an abnormal state when the determination result information of the determination result buffer 16b indicates abnormality. And a determination output processing unit 16c for controlling the output means 14 to notify the outside of the situation. Here, only the display unit 14 is disclosed as output means, but it may be an external alarm notification device, wireless communication device, or the like, or a configuration including these devices.

  As shown in FIG. 7, the flow amount increase / decrease determination unit 16a treats the number of frames according to the average value setting parameter (Pa) and the congestion rate (Rc0, Rc1, Rc2,..., Rcn) of a plurality of frames in the time series range. Function for calculating the average congestion rate (Rc_0, Rc_1, Rc_2,..., Rc_n), and calculating the comparison target congestion rate (RcPast) for a plurality of frames in the time series range and the number of frames according to the comparison target parameter (Pb) Processing function, a difference function between the current (latest) average congestion rate (Rc_n) and the comparison target congestion rate (RcPast), and a threshold value in which the value of the difference processing result is preset as an increase / decrease parameter as shown in FIG. And a processing function for determining whether or not it is within the range of (Th1, Th2).

  The flow rate increase / decrease determination unit 16a uses the flow rate data stored in the congestion rate buffer 15c of the flow image processing unit 15 as the current congestion rate to determine a certain amount of congestion rate (Rc0, Rc1, Rc2, ... Rcn) buffer memory area (Ba), and current and past congestion rates stored in this buffer memory area (Ba), the number of frames according to the average value setting parameter (Pa) and a plurality of time series range congestions Calculation processing means for calculating an average congestion rate (R_cn) based on the rate, a buffer memory area (Bb) holding the calculated average congestion rate (R_cn), and the number of frames and time series according to the comparison target parameter (Pb) Calculation processing means for calculating an average value of a plurality of past average congestion rates based on a plurality of average congestion rates in a range (eg, Rc_0, Rc_1, Rc_2), and the calculated value as a comparison target congestion The comparison target congestion rate calculation processing means and buffer memory area (Bc) held as (RcPast), and the difference between the current average congestion rate (Rc_n) and the comparison target congestion rate (RcPast) are taken, and the values are shown in FIG. It is determined whether it is within the range of thresholds Th1 and Th2 set in advance as increase / decrease parameters, or exceeds (deviates) the above range, and the amount of water flowing in the channel 1 is in a normal state within the set range. And processing means for outputting determination result information indicating whether there is an abnormal state exceeding the set range.

  A processing procedure of the flowing water monitoring system having the above configuration will be described with reference to a flowchart shown in FIG.

  The camera 11 captures an image of the water channel 1 to be monitored at a certain position and angle of view, and captures the fluctuation of the water in the flowing water (Wb) portion of the water channel 1 as an image accompanied by luminance fluctuation due to irregular reflection of light. Here, the images of the flowing water (Wb) portions at the head portions 1h, 1h,..., 1h of the outlets 1d, 1d,.

  Images captured by the camera 11 are captured by the capture unit 12 in units of frames and stored in the image buffer 15a of the image processing unit 13.

  The congestion rate deriving unit 15b cuts out images of the flowing water (Wb) portion one by one from the image stored in the image buffer 15a as an image pi (i = 1, 2,..., N), and extracts the flowing water (Wb) portion. The fluctuation of the water is captured from the video and quantized to calculate the degree of fluctuation of the water as a congestion rate, and this calculated value (congestion rate) is stored in the congestion rate buffer 15c (step S1).

  The flowing water amount increase / decrease determination unit 16a reads the current frame congestion rate (Rcn) from the congestion rate buffer 15c each time the video frame of the image buffer 15a is updated, and the current average congestion rate including the congestion rate (Rcn). (Rc_n) is calculated, the comparison target congestion rate (RcPast) is updated, and the difference between the updated comparison target congestion rate (RcPast) and the current average congestion rate (R_cn) is calculated (step S3), and the difference is generated. (Yes in step S3), it is determined whether or not the value is within the range of the increase / decrease parameters (Th1, Th2), and the determination result information is stored in the determination result buffer 16b (step S4).

  The flow amount increase / decrease determination unit 16a sequentially performs the above-described processing (steps S2 to S4) for each of the cut-out images p1, p2, ..., pn of the m outlets 1d, 1d, ..., 1d. Run repeatedly.

  The determination output processing unit 16c includes a predetermined output means (for example, an alarm) that includes a display unit 14 to notify the outside that the amount of water flowing in the water channel 1 has entered an abnormal state when the determination result information in the determination result buffer 16b indicates abnormality. (Informing device, wireless communication device, etc.). Further, the normality / abnormality of the water flow amount is displayed on the display screen of the display unit 14 for each of the water outlets 1d, 1d,..., 1d of the m water channels even in the steady state (step S5).

  As described above, it is possible to realize an image processing mechanism that recognizes the degree of water fluctuation from an image captured by the monocular camera 11 and quantizes it to determine an abnormality in the amount of flowing water, thereby providing a sensor directly in the flowing portion of the water channel. Without being able to efficiently detect and report an abnormal flow of water in the water channel being monitored with an economically advantageous configuration, and using a single imaging camera for a plurality of water channels being monitored With the system configuration, it is possible to efficiently detect and notify an abnormality of flowing water in each water channel for each water channel.

  The above-described embodiment is image processing for recognizing the degree of water fluctuation from an image photographed by the monocular camera 11 and quantizing it to determine an abnormality in the amount of water flow.

  Other embodiments (Examples 1 and 2) of the present invention to which image processing technology for recognizing fluctuation of water from the above frame image and quantizing and judging an abnormality in the amount of flowing water are described with reference to FIGS. Is shown below. Here, FIG. 1 is used for the components of the entire system.

  FIG. 8 shows a subject to be photographed by the camera 11 according to the first embodiment. Here, the water channel (C) is photographed obliquely from above including a part of the road shoulder (Bk). FIG. 9 shows a video frame taken by the camera 11, and in this video frame 14a, flowing water flowing through the shoulder (Bk) of the water channel (C) and the water channel (C) is imaged. Here, the illumination lamp 2 is attached to the camera 11 to illuminate the water surface of the water channel (C).

  The image processing unit 13 cuts out a rectangular region having a fixed width that defines a horizontal width from the video frame 14a photographed by the camera 11, and uses the image of the cut out region as a processing target image to capture and quantize water surface fluctuations. . Based on the quantized value, the highest position coordinate (W) of the fluctuations in the horizontal direction on the video frame 14a shown in FIG. 9 is specified. The uppermost position coordinate (W) of the fluctuation changes on the video frame 14a according to the amount of water flowing in the water channel (C) (WH-WL). Whether the uppermost position coordinate (W) of the fluctuation is between the position coordinate (DL) for determining the upper limit water flow amount in the vertical direction set in advance on the video frame 14a and the position coordinate (DR) for determining the lower limit water flow amount Whether or not is determined by difference processing. When the position coordinate (W) exceeds the position coordinate (DR), an alarm is issued.

  FIG. 10A shows a subject to be photographed by the camera 11 according to the second embodiment. Here, the water channel (C) that is a subject to be photographed has an inclined surface on the road side, and the road to the shoulder (Bk). The bottom has a narrow channel structure. The water channel (C) is photographed from obliquely above including a part of the road shoulder (Bk). FIG. 10 (b) shows a video frame taken by the camera 11, and the video frame 14b flows through the water shoulder (Bk) of the water channel (C) and the water channel (C) of some road side surfaces. The running water is imaged.

  The image processing unit 13 captures and quantizes the fluctuation of the water surface from the video frame 14 b photographed by the camera 11. Based on the quantized values, the position coordinates (W = position coordinates of both ends) of the width of fluctuation continuously extending in the horizontal direction intersecting the set vertical position coordinates on the video frame 14b shown in FIG. . The position coordinate (W) of the fluctuation width changes on the video frame 14a according to the amount of water flowing in the water channel (C). Whether or not the position coordinate (W) of the fluctuation width is between the position coordinate (DL) for determining the upper limit water flow amount in the vertical direction and the position coordinate (DR) for determining the lower limit water flow amount set in advance on the video frame 14a. Is determined by difference processing. When the position coordinate (W) exceeds the position coordinate (DR), an alarm issuing process is performed by alarm notification or the like.

  The flowing water monitoring system according to the other embodiments 1 and 2 described above is not limited to an industrial waterway, and can be widely applied to waterways such as irrigation waterways and general rivers.

  Here, the configuration and operation of the congestion rate deriving unit 15b using the noise detection technique according to the above-described embodiment will be described with reference to FIGS.

  The congestion rate deriving unit 15b sequentially inputs the images taken by the camera 11, extracts the flowing water image as a processing target image for the plurality of input images within a certain period, and extracts the processing target image. Automatic calculation of pixel-based automatic thresholds that vary with luminance variations based on the set minimum threshold upper limit value, and luminance distribution information for the corresponding pixels of the plurality of processing target images within the predetermined period The luminance distribution information calculated by the threshold calculation processing unit and the automatic threshold calculation processing unit is extracted at a constant sampling period, and the average luminance dispersion per pixel and the standard of luminance dispersion are extracted for a plurality of pieces of luminance distribution information in a set time unit. Based on the fluctuation information calculation unit for calculating the deviation, the minimum threshold upper limit value and the average luminance dispersion calculated by the fluctuation information calculation unit and the standard deviation of the luminance dispersion, the above processing is performed. For each pixel of the target image, it is determined whether the pixel is a stable pixel, a variable pixel, or an over-variable pixel, and the occupation rate of the over-variable pixel is set as a congestion rate (= degree of water fluctuation) in the processing target image. And a pixel determination unit for calculation.

  In an image processing apparatus having an area extraction processing function for extracting a rectangular area including a change pixel from a plurality of time-series images captured by a monocular camera (one camera), the applicant of the present invention For each pixel, the average luminance value and standard deviation per pixel are calculated, and the calculated standard deviation for each pixel is set to the threshold value of the corresponding pixel for extracting the change pixel (for each pixel that varies with luminance variation). By setting the threshold to (automatic threshold), an image processing technique with improved tracking performance of the moving object was realized (see Japanese Patent Application Laid-Open No. 2008-250892). A stationary object that is capable of detecting a stationary object from the current image and the past image, distinguishing the stationary object from the moving object, and displaying it on the screen by applying the image processing technology equipped with this automatic threshold calculation processing function. The detection processing function was realized (Japanese Patent Application No. 2009-046885). Furthermore, by applying the image processing technology provided with the automatic threshold calculation processing function as an extension technology of this stationary object detection processing function, the degree of congestion of a moving object (for example, the degree of congestion of a person in a public use facility or the like) is detected, An attempt was made to develop a congestion detection / determination function that can notify an external device that it is congested. In the stationary object detection processing function, pixels with a large amount of movement have large luminance value dispersion (dispersion), and pixels with no movement have a small luminance value variation within a narrow low luminance range. The luminance variance value and standard deviation per pixel are calculated for multiple images within a certain period of time, and this luminance variance value or standard deviation is used as a threshold value. Pixels with a large variance are discarded, and only a pixel that is stably within a low luminance range with a low luminance is regarded as a background pixel and extracted to create a background image by a set of pixels.

  The image processing apparatus according to the embodiment of the present invention investigates the luminance fluctuation state of the input video using the automatic threshold value of the pixel unit that fluctuates with the luminance fluctuation as a reference value, and determines the flow state (fluctuation state), the congestion state ( It has a congestion detection determination function that detects three states of a crowded state) and a stable state (non-moving state). The flow state can be detected by monitoring a threshold variation (a state in which a threshold average variation is large) of a variation pixel (a pixel with a transient motion). The congestion state (busy state) can be detected by monitoring threshold fluctuations (state in which the threshold average is high and stable) of over-variable pixels (pixels that are continuously fluctuating = pixels with fluctuations). The stable state (steady state) can be detected by monitoring the threshold variation (a state where the average threshold is low and stable) of the stable pixel (non-variable pixel).

  Embodiments of the present invention will be described below with reference to the drawings. In this embodiment, image data for one frame (one screen) captured from a camera (monocular camera) is simply referred to as an image, an image on the screen, or an image for one screen.

  As shown in FIG. 11, the image processing apparatus according to the embodiment of the present invention includes a camera 11, a capture unit 12, an image processing unit 13, and a display unit 14.

  The camera 11 includes a lens unit and an image pickup device (for example, a CCD solid-state image pickup device or a CMOS image sensor) provided at an image forming position of the lens unit, so that a subject (animal body) that moves outdoors or indoors can be used. A captured image for one screen is output to a target in a predetermined pixel unit (for example, one frame 320 × 240 pixels = QVGA).

  The capture unit 12 has a processing function of capturing an image in units of frames captured by the camera 11 as a processing target image (input image) of the image processing unit 13 and holding the image in an image buffer described later.

  The image processing unit 13 includes a variable pixel extraction processing function unit 13A, a congestion detection processing function unit 13B, and a determination processing function unit 13C. The variable pixel extraction processing function unit 13A targets a plurality of input images (video frames according to the number of frames set by the average value setting parameter (Pa) shown in FIG. 7 and the time series range) within a certain period of time. For the processing target image excluding the mask area, an automatic threshold value is calculated for each pixel that fluctuates according to the luminance variation, and luminance dispersion information for the corresponding pixels of the plurality of processing target images within the predetermined period is calculated, and the calculated luminance A dispersion function is extracted at a constant sampling period, and a processing function for calculating an average luminance dispersion per pixel and a standard deviation of luminance dispersion for a plurality of pieces of luminance dispersion information in a set time unit is realized.

  In calculating this automatic threshold, the minimum threshold upper and lower limit values are given as parameters. The minimum threshold value is obtained from the average value and variance or standard deviation of the variance or standard deviation of the luminance value obtained for each pixel in the process of automatic threshold calculation. The lower limit value of the threshold value set for each pixel Is the value given as The minimum threshold upper and lower limit values are parameters that are the upper and lower limit values of the obtained minimum threshold. The minimum threshold lower limit value is set to suppress excessive detection of noise, and the minimum threshold upper limit value is surely the difference in luminance. Set to define the deviation to be taken as. The minimum threshold upper limit value given as this parameter is used as a determination value threshold for stable pixels, flow pixels, and congested pixels.

  The congestion detection processing function unit 13B extracts the luminance dispersion information calculated by the variable pixel extraction processing function unit 13A at a constant sampling period, and the average luminance dispersion and luminance per pixel for the extracted plurality of luminance dispersion information in a set time unit. A standard deviation of the variance is calculated, and based on the average luminance variance and the standard deviation of the luminance variance and the threshold (minimum threshold upper limit value) used in the calculation of the variation pixel extraction processing function unit 13A, the processing target image A processing function for determining whether the pixel is a stable pixel, a variable pixel, or an over-variable pixel, and occupancy of each pixel in the processing target image for the determined stable pixel, variable pixel, or over-variable pixel A processing function for calculating the rate and determining a congestion state exceeding the set congestion rate based on the calculated occupation ratio of the over-variable pixels is realized. The determination processing function unit 13C realizes the processing function of the determination processing unit 16 shown in FIG.

  The display unit 14 displays the congestion state determined by the determination processing function unit 13C. For example, the drawing information indicating the congestion state is displayed together with the captured image collected and stored together with the corresponding congestion log. Also, congestion determination result for each pixel (stable / flow / congested), block-based congestion determination result (stable / flow / congested), flow detection state, congestion detection state, flow block occupancy, congestion block occupancy, for each pixel Threshold, average threshold, threshold standard deviation, block / flow / congested pixel count, processing target pixel count, entire screen processing target pixel count, flow / congested pixel count, stable / variation / overvariable state image of each pixel, Detailed information such as a stable / flow / congested state image of each block can be presented to the user.

  FIG. 12 shows the configuration of each functional unit in the image processing unit 13 described above. In the embodiment shown in FIG. 12, in addition to the pixel-by-pixel congestion determination processing function in the processing target image, a functional configuration having a congestion determination processing function in units of divided areas obtained by dividing the processing target image into a plurality of blocks. Is illustrated.

  The image processing unit 13 includes an image buffer memory 130a and an automatic threshold value calculation processing unit 131 that constitute a fluctuation pixel extraction processing function unit 13A, a fluctuation information calculation unit 132 that constitutes a congestion detection processing function unit 13B, a congestion pixel extraction unit 133, A congestion block calculation unit 134, a congestion rate deriving unit 135, and a congestion determination data memory 130b are provided.

  The image buffer memory 130a stores, as an input image, a plurality of frames in a time series as frame-by-frame images captured by the capture unit 12 at a certain timing. A mask area that does not require congestion detection processing is set for the input image stored in the image buffer memory 130a, and each pixel in the processing target image area excluding the image of the mask area is a processing target pixel for congestion detection. Become. Further, in this image buffer memory 130a, an original image (spatial differential image) or an edge image (contour image) is stored as an input image according to the input image selection designation of the external input parameter, and the automatic threshold value calculation processing unit 131 stores the original image. An automatic threshold for images or an automatic threshold for edge images is calculated.

  The automatic threshold value calculation processing unit 131 targets a plurality of images (original image or edge image) within a certain period stored in the image buffer memory 130a, and the pixel that varies with luminance variation for the processing target image excluding the mask area. An automatic threshold value calculation unit for calculating an automatic threshold value (including a minimum threshold value for extracting a stable pixel having low luminance), and calculating luminance dispersion information for corresponding pixels of a plurality of processing target images within the predetermined period. A variation pixel calculation unit that extracts the calculated luminance dispersion information at a constant sampling period and calculates an average luminance dispersion per pixel and a standard deviation of the luminance dispersion for a plurality of pieces of luminance dispersion information in a set time unit extracted. Configured.

  The automatic threshold value calculation unit in the automatic threshold value calculation processing unit 131 is realized by the automatic threshold value setting technique described in Japanese Patent Application Laid-Open No. 2008-250892 proposed by the inventor of the present application. For a plurality of pixels within a certain period, the average luminance value and standard deviation per pixel are calculated, and the calculated standard deviation for each pixel is set as the threshold value of the corresponding pixel for extracting the change pixel. Yes. In the process of calculating the automatic threshold value, in order to eliminate the influence of noise on the image, it is obtained from the average value and variance or standard deviation of the luminance value variance or standard deviation obtained for each pixel. It is characterized by being given as a lower limit value of a threshold value set in a pixel. The minimum threshold upper / lower limit is a parameter used as the upper and lower limit values of the obtained minimum threshold. The minimum threshold lower limit value is set to suppress excessive detection of noise, and the minimum threshold upper limit value is surely Set to define the deviation to be taken as the difference.

  The automatic threshold value set by the automatic threshold value setting technique described in Japanese Patent Application Laid-Open No. 2008-250892 is automatically set to a high threshold value for a pixel having a large variation in luminance. Set a low and stable threshold.

  In the embodiment of the present invention, the minimum threshold upper limit value described in JP 2008-250892 A is used as a threshold (FTh) used as reference information for congestion detection.

  Although not shown, the automatic threshold value calculation processing unit 131 is provided with an automatic threshold value calculation processing buffer. In the automatic threshold value calculation processing buffer, various data in the middle of calculation used for automatic threshold value calculation processing are provided. An area for storing internal parameters and the like, an area for storing external input parameters, and the like are provided. As an example of external input parameters, the image type of difference processing (for example, 1; original image, 2; edge image), the number of reference frames for calculating an automatic threshold (for example, the number of reference frames (n) = 12) Various parameter values such as the minimum threshold upper and lower limit values for the original image and the minimum threshold upper and lower limit values for the edge image for setting the automatic threshold fluctuation range are set.

  The variable pixel calculation unit in the automatic threshold calculation processing unit 131 performs read (R) access to the image buffer memory 130a, and the luminance distribution for the corresponding pixels of the plurality of processing target images within the predetermined period stored in the image buffer memory 130a. Information (luminance dispersion value BTi) is calculated and stored in a data buffer provided inside the automatic threshold value calculation processing unit 131.

  The variation information calculation unit 132 reads the luminance variance information (luminance variance value BTi) stored in the internal data buffer of the variation pixel extraction unit 131 at a constant sampling period according to the frame interval and the number of frames set by the external input parameters. (R) (extract), and calculate the average luminance dispersion per pixel and the standard deviation of the luminance dispersion for a plurality of pieces of luminance dispersion information (luminance dispersion value BTi) in a set time unit. The average luminance dispersion value is set as an average threshold value (μBTi) in pixel units, and the standard deviation value of luminance dispersion is set as the standard deviation (σBTi), and is written (W) to the image variation information data area b1 of the congestion determination data memory 130b. It has a processing function to memorize.

  The congestion pixel extraction unit 133 calculates the average threshold value (μBTi) and standard deviation (σBTi) of each pixel from the image variation information data area b1 of the congestion determination data memory 130b for the threshold value (FTh) input from the variation pixel extraction unit 131. Read (R), threshold (FTh) as a reference value, average threshold (μBTi) and standard deviation (σBTi) as a determination threshold, and whether the pixel is a stable pixel, a variable pixel, or an over-variable pixel It has a processing function for making a determination and writing (W) and storing the determination result data (congestion determination data) in the congestion determination data area b2 of the congestion determination data memory 130b.

  The congestion block calculation unit 134 reads (R) the congestion determination data stored in the congestion determination data area b2 of the congestion determination data memory 130b, and the stable pixel, the variation pixel, and the over-variation pixel determined by the congestion pixel extraction unit 133. For each image area obtained by dividing the image into blocks by a plurality of pixels, the occupancy rate of stable pixels, the occupancy rate of variable pixels, and the occupancy rate of over-variable pixels are calculated. (Determination data) is written (W) and stored in the congestion determination data area b3 of the congestion determination data memory 130b.

  The congestion rate deriving unit 135 performs read (R) access to the congestion determination data stored in the congestion determination data area b3 of the congestion determination data memory 130b, and the occupation ratios of the stable pixels and the fluctuating pixels calculated by the congestion block calculation unit 134. Based on the occupation ratio of the over-variable pixels, it has a processing function of determining a congestion state exceeding the set congestion rate and displaying it on the display unit 14. The buffer (BUF) 135c shown in the congestion rate deriving unit 135 corresponds to the congestion rate buffer 15c shown in FIG.

  The determination processing unit 136 realizes the processing function of the determination processing unit 16 shown in FIG. The buffer (BUF) 136b shown in the determination processing unit 136 corresponds to the determination result buffer 16b shown in FIG.

  In the congestion determination data memory 130b, in addition to the above-described data areas b1 to b3, an image data storage area for storing congestion detection determination image data, mask image data, and the like, an execution flag (for example, flow detection) A parameter storage area for storing processing execution flags, congestion detection processing execution flags, and the like, and parameters for storing operation parameters (for example, original image / edge image setting parameters, congestion determination frame interval setting parameters, flow determination parameters, congestion determination parameters, etc.) A storage area, a counter area used as an arithmetic processing counter (for example, a congestion detection processing counter, a processing frame interval determination counter, etc.), and other arithmetic processing buffers, pointers, etc. used for congestion detection determination processing are stored. A work area for the congestion detection determination process is provided.

  The image processing apparatus according to the embodiment of the present invention investigates the luminance fluctuation state according to the state of the input video, and detects three states of a fluid state (fluctuating state), a crowded state (busy state), and a stable state (non-moving state). By doing so, a congestion detection determination function that performs congestion detection is realized.

(1). Congestion determination processing operation in units of pixels The variable pixel extraction unit 131 that is a component of the variable pixel extraction processing function unit 13A provided in the image processing unit 13 includes a plurality of images (in a certain period of time) stored in the image buffer memory 130a ( With respect to the processing target image excluding the mask area for the original image or the edge image), luminance dispersion information (luminance dispersion value BTi) in units of pixels that varies with the luminance variation is calculated and stored in the internal data buffer.

  The variation information calculation unit 132, which is a component of the congestion detection processing function unit 13B, uses the luminance dispersion information (luminance variance value BTi) stored in the internal data buffer of the variation pixel extraction unit 131 as a frame set by an external input parameter. Extracted at a constant sampling period according to the interval and the number of frames, and calculated the average luminance dispersion per pixel and the standard deviation of the luminance dispersion for the plurality of luminance dispersion information (luminance dispersion value BTi) in the set time unit, and calculated the average Write (W) to the image variation information data area b1 of the congestion determination data memory 130b with the value of luminance dispersion as the average threshold value (μBTi) in pixels and the standard deviation value of luminance dispersion as the standard deviation (σBTi).

  The congestion pixel extraction unit 133, which is a constituent element of the congestion detection processing function unit 13B, receives a threshold value (FTh) from the variation pixel extraction unit 131, and from the image variation information data area b1 of the congestion determination data memory 130b, The average threshold value (μBTi) and the standard deviation (σBTi) are read (R), the threshold value (FTh) is used as a reference value, the average threshold value (μBTi) and the standard deviation (σBTi) are set as determination threshold values, and the pixel is a stable pixel, It is determined whether the pixel is a variation pixel or an excessive variation pixel, and data (congestion determination data) of the determination result is written (W) to the congestion determination data area b2 of the congestion determination data memory 130b.

  FIG. 13 and FIG. 14 show threshold fluctuations assumed in the determination of the pixel state of the stability / fluctuation / over fluctuation. Here, the determination threshold value of the average threshold value (μBTi) is set to threshold value (FTh) = the minimum threshold value upper limit value, and the determination threshold value of standard deviation (σBTi) is set to the minimum threshold value upper limit value × ½.

  As shown in FIGS. 13A and 13B, when μBTi and σBTi are both less than the determination threshold, it is determined as “stable pixel”, and when σBTi is equal to or higher than the determination threshold, it is determined as “fluctuating pixel”. When the value is equal to or greater than the determination threshold value and σBTi is less than the determination threshold value, the pixel is determined as an “over-change pixel” that continuously varies.

  FIGS. 14A, 14B, and 14C illustrate the threshold variation state of the stable pixel, the variation pixel, and the excessive variation pixel. As shown in FIGS. 13B and 14A, the threshold value of the stable pixel has a threshold fluctuation characteristic in which the average threshold value is low and the standard deviation is also small. As shown in FIGS. 13B and 14B, the threshold value of the variable pixel has a threshold value fluctuation characteristic in which the threshold value varies greatly and the standard deviation is large. As shown in FIGS. 13 (b) and 14 (c), the threshold value of an over-variable pixel in which pixels with movement continuously vary has a threshold variation characteristic with a high average threshold value.

  The congestion rate deriving unit 135 reads (R) the congestion determination data stored in the congestion determination data area b3 of the congestion determination data memory 130b, and determines the occupancy ratio and the excess of the stable pixels and the fluctuation pixels calculated by the congestion block calculation unit 134. Based on the occupancy rate of the fluctuating pixels, a congestion state exceeding the set congestion rate is determined and displayed on the display unit 14.

  As described above, in synchronization with the threshold value calculation processing timing of the input image (original image / edge image), the time sampling of the threshold value obtained for each pixel (the acquisition cycle is the automatic cycle of the threshold calculation frame number × the threshold calculation block size). The average threshold value (μBTi) and standard deviation (σBTi) for the number of samples to be evaluated are external parameters), and using this information and the threshold value (FTh), the state of stable / fluctuating / over-varying pixels in pixel units is obtained. By determining and determining the degree of congestion from the ratio (occupation ratio) of over-variable pixels in the processing target image, a highly reliable congestion determination rate can be detected. If the threshold value based on the original image (brightness) is used, it is possible to detect soot, fog, and smoke that are about the fluctuation in brightness. If the threshold value based on the edge image (contour) is used, fluctuations in various moving objects can be captured. It becomes possible.

(2). Congestion determination processing operation in block units The congestion block calculation unit 134, which is a constituent element of the determination processing function unit 13C, reads (R) the congestion determination data stored in the congestion determination data area b2 of the congestion determination data memory 130b, and performs congestion. For stable pixels, variable pixels, and over-variable pixels determined by the pixel extraction unit 133, the stable pixel occupation rate, variable pixel occupation rate, over-variable pixel occupation for each image region obtained by dividing the image into blocks in units of a plurality of pixels. The rate is calculated, and the calculated data (occupancy determination data) of each block is written (W) in the congestion determination data area b3 of the congestion determination data memory 130b.

  In this block unit processing, the processing target image is divided into a plurality of blocks in order to detect congestion. Here, as an example, as shown in FIG. 15, one QVGA frame (320 × 240 pixels) is divided into 30 × 40 blocks (1200 blocks) with 8 pixels × 8 pixels as one block, and divided blocks. The number of stable / fluctuating / over-varying pixels and processing target pixels within (excluding mask pixels) is managed. With this data, various determinations in units of blocks are possible. In other words, the area of the designated block is used as the denominator, and the occupation rate and the degree of congestion are determined using the number of variable pixels and excessively variable pixels generated in the block. The occupancy ratio calculation means in this block determination process is shown in FIG. Here, the stable pixel occupancy is [Σ stable pixel / Σ (number of processed pixels (excluding mask area))], the variable pixel occupancy is [Σ changed pixel / Σ (number of processed pixels (excluding mask area))], The variable pixel occupancy is calculated by [Σ over-variable pixels / Σ (number of processed pixels (excluding mask area))], and the state with the highest stable pixel occupancy, variable pixel occupancy, and over-variable pixel occupancy is determined for the block. State.

  The congestion rate deriving unit 135 reads (R) the congestion determination data stored in the congestion determination data area b3 of the congestion determination data memory 130b, and determines the occupancy ratio and the excess of the stable pixels and the fluctuation pixels calculated by the congestion block calculation unit 134. Based on the occupancy rate of the fluctuating pixels, a congestion state exceeding the set congestion rate is determined and displayed on the display unit 14.

  Here, screen display and final determination are performed based on the result of the block unit. “Flow determination rate” and “congestion determination rate” indicate the ratio of flow blocks and congestion blocks to the block to be processed, and are external input parameters for detecting congestion (10% to 100% when 1 to 10 are set) Mean). The determination formula of “flow” is shown in FIG. 17, and the determination formula of “congestion” is shown in FIG. This parameter makes it possible to determine a two-stage change (flow <congestion priority). FIG. 19 illustrates the specifiable range of the “flow” determination parameter and the “congestion” determination parameter.

  Also, the flow / congestion determination / release determination is performed in consideration of temporal continuity (determination time, release time) depending on the state of each frame. FIG. 20 shows processing timings for confirming / releasing the flow / congestion state and log and image storage.

  Here, an image and a log at the time when the flow / congestion is determined are stored. Since the sensitivity setting for flow / congestion depends on the input video and processing results, it is expected that adjustment will be difficult, so the log at the time of confirmation of flow / congestion against the default setting (setting 5: 50%) And the image at that time, and the flow determination rate / congestion determination rate are drawn and stored in the image. Here, image storage for one frame is performed, but image storage for a plurality of frames may be performed. Note that the flow / congestion log can be stored periodically, and the maximum flow determination rate / congestion determination rate and the image at that time generated between the previous storage and the new storage are stored as a log. In addition, it is possible to set whether to save each log of flow and congestion.

  Note that the present invention is not limited to the above-described embodiment as it is, and can be embodied by modifying the constituent elements without departing from the scope of the invention in the implementation stage. In addition, various inventions can be formed by appropriately combining a plurality of components disclosed in the embodiment. For example, some components may be deleted from all the components shown in the embodiment. Furthermore, you may combine a component suitably in different embodiment. Further, the method described in the above embodiment can be stored and distributed in a storage medium such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory as a program that can be executed by a computer.

  DESCRIPTION OF SYMBOLS 1 ... Waterway, 1d ... Water outlet, 1h ... Head part, 2 ... Illumination lamp, 11 ... Camera (monocular camera), 12 ... Capture part, 13 ... Image processing part, 14 ... Output means (display part), 13A ... Fluctuation Pixel extraction processing function unit, 13B ... congestion detection processing function unit, 13C ... determination processing function unit, 15 ... running water image processing unit, 15a ... image buffer, 15b ... running water amount derivation processing unit (congestion rate derivation unit), 15c ... running water Volume buffer (congestion rate buffer), 16 ... determination processing unit, 16a ... flow amount increase / decrease determination unit, 16b ... determination result buffer, 16c ... determination output processing unit, 130a ... image buffer memory, 130b ... congestion determination data memory, b1 ... Image fluctuation information data area, b2 ... congestion determination data area, b3 ... congestion determination data area, 131 ... fluctuation pixel extraction section, 132 ... fluctuation information calculation section, 133 ... congestion pixel extraction section, 1 4 ... Congested block calculation unit, 135 ... Congestion determination processing unit, FTh ... Threshold value (minimum threshold upper limit value), μBTi ... Average threshold value (average luminance variance), σBTi ... Standard deviation (standard deviation of luminance variance), p1, p2, ..., pn ... cut-out image, Wb ... flowing water, Pa ... average value setting parameter, Pb ... comparison target parameter.

Claims (11)

A monocular camera that captures an image of the flowing water part of the waterway,
Image processing means for capturing and quantizing water fluctuations from an image of a flowing water image taken by the monocular camera;
A running water monitoring system comprising: a judgment processing unit for judging whether or not the amount of water flowing in the water channel is in a normal state using the value obtained by the image processing unit as judgment target data.   2. The camera according to claim 1, wherein the camera simultaneously photographs a flowing portion of each water channel with respect to a plurality of water channels, and the image processing unit quantizes water fluctuation for each water flow of each water channel. Running water monitoring system.   The flowing water monitoring system according to claim 1 or 2, wherein the camera photographs a flowing water portion of a head portion at a water outlet of the water channel.   The running water monitoring system according to any one of claims 1 to 3, further comprising illumination means for illuminating a running water portion of the water channel in conjunction with the operation of the camera.   2. The image processing means includes processing means for extracting luminance fluctuation pixels from a plurality of time-series processing target images taken by the camera and capturing water fluctuations from the luminance fluctuation pixels. The running water monitoring system described in 1. The image processing means includes
The images taken by the camera are sequentially input, and the flowing water portion image is extracted as a processing target image for the plurality of input images within a certain period, and the set minimum threshold upper limit value is set for the extracted processing target image. Based on the above, an automatic threshold value calculation processing unit that calculates an automatic threshold value for each pixel that fluctuates with luminance fluctuation, and calculates luminance dispersion information for corresponding pixels of the plurality of processing target images within the predetermined period;
Fluctuation information for extracting the luminance distribution information calculated by the automatic threshold value calculation processing unit at a constant sampling period, and calculating the average luminance dispersion per pixel and the standard deviation of the luminance dispersion for the extracted plurality of luminance distribution information in a set time unit. A calculation processing unit;
Based on the minimum threshold upper limit value and the average luminance variance calculated by the fluctuation information calculation unit and the standard deviation of the luminance variance, for each pixel of the processing target image, the pixel is a stable pixel, a fluctuation pixel, or an over-variation pixel. A pixel determination processing unit that determines which is determined, and calculates the occupancy of each pixel in the processing target image for the determined stable pixel, variable pixel, and excessively variable pixel;
Comprising
The determination processing means includes:
Flow rate determination processing for determining whether or not the flow rate of the channel is in a normal flow rate state within an allowable range in which the flow rate of the water channel is set as determination target data using the occupancy rate of the over-variable pixels calculated by the pixel determination processing unit The flowing water monitoring system according to claim 1, further comprising a section.   The pixel determination processing unit sets the average luminance variance as an average threshold μBTi, the standard deviation of the luminance variance as a standard deviation σBTi, a determination threshold of μBTi as the minimum threshold upper limit, and a determination threshold of σBTi as the minimum threshold upper limit × As 1/2, when both μBTi and σBTi are less than the determination threshold, the pixel is determined to be stable, and when σBTi is equal to or greater than the determination threshold, the pixel is determined to be a variation pixel, and when μBTi is greater than or equal to and less than σBTi, the variation continues. The flowing water monitoring system according to claim 6, wherein it is determined that the pixel is an excessively fluctuating pixel. A monocular camera that shoots the water surface of the channel from diagonally above;
Processing means for capturing and quantizing fluctuations of the water surface from the frame-by-frame images taken by the camera;
Image processing means for specifying the highest position coordinates of fluctuations in a horizontal direction on a frame of an image photographed by the camera based on the quantized values;
Determination means for determining the amount of water flowing in the water channel based on the difference between the highest position coordinate of the fluctuation specified by the image processing means and the set position coordinate in the vertical direction on the frame;
A running water monitoring system characterized by comprising: A monocular camera that shoots the water surface of the channel from diagonally above;
Processing means for capturing and quantizing fluctuations of the water surface from the frame-by-frame images taken by the camera;
Image processing means for specifying the position coordinates of the fluctuation width in the horizontal direction at the set position in the vertical direction on the frame of the image captured by the camera based on the quantized value;
Determination means for determining the amount of water flowing in the channel based on the difference between the position coordinate of the fluctuation width specified by the image processing means and the position coordinate of the horizontal setting width at the setting position on the frame;
A running water monitoring system characterized by comprising: A water flow monitoring program for causing a computer to function as a water flow monitoring system for monitoring the amount of water flow in the water channel based on an image of the water channel photographed with a monocular camera,
An image processing function that captures and quantifies fluctuations of water from an image of a flowing water part of a water channel photographed by the camera;
A flow monitoring program for causing a computer to realize a determination processing function for determining whether or not the amount of flowing water in the water channel is in a normal state using the value obtained by the image processing function as determination target data. The image processing function is:
The images taken by the camera are sequentially input, and the flowing water portion image is extracted as a processing target image for the plurality of input images within a certain period, and the set minimum threshold upper limit value is set for the extracted processing target image. Based on the above, an automatic threshold value calculation processing function for calculating an automatic threshold value in units of pixels that fluctuates with luminance fluctuations, and calculating luminance dispersion information for corresponding pixels of the plurality of processing target images within the predetermined period;
Fluctuation information that extracts the luminance dispersion information calculated by the automatic threshold value calculation processing function at a constant sampling period, and calculates the average luminance dispersion per pixel and the standard deviation of the luminance dispersion for the plurality of extracted luminance dispersion information in a set time unit. A calculation processing function;
Based on the minimum threshold upper limit value and the average luminance variance calculated by the variation information calculation processing function and the standard deviation of the luminance variance, for each pixel of the processing target image, the pixel is a stable pixel, a variable pixel, an over-variable pixel A pixel determination processing function for determining the occupancy rate of each pixel in the processing target image for the determined stable pixel, variable pixel, and excessively variable pixel.
The determination processing function is:
A flow rate determination processing function for determining whether or not the flow rate of the water channel is in a normal flow rate state within an allowable range in which the flow rate of the water channel is set as determination target data using the occupancy rate of the over-variable pixels calculated by the pixel determination function. The running water monitoring program according to claim 9, further comprising:

Images