Measurement program, measurement method, and information processing device

Abstract

To decide the movement speed of a float flowing in a river using a moving image.SOLUTION: An information processing device according to one embodiment comprises: a setting unit which sets a measurement line expressing the height of a water level of a river on the basis of a position where a line segment expressing a side wall of the river at a prescribed distance from a photographing apparatus intersects the water level of the river in a frame image of a moving image obtained by photographing the river by the photographing apparatus; a measurement unit which measures the movement time in which a float flows in a prescribed section from a start measurement line to an end measurement line by using the measurement line as at least one of the start measurement line and end measurement line for measuring the flow speed with the float flowing in the river; and a decision unit which decides a flow amount of the river using the movement time and the length of the prescribed section.SELECTED DRAWING: Figure 4

Description

[Technical Field]

[0001] The present invention relates to a measurement program, a measurement method, and an information processing device. [Background technology]

[0002] In order to grasp conditions in rivers, such as when the water level rises, a float is floated in a predetermined section, and the float's speed, which represents the river's flow velocity, is obtained from the time it takes for the float to pass through the section.The river's flow rate is then determined from the speed of movement and the cross-sectional area of the river.

[0003] In this regard, a technique for understanding the state of a river using video is known (for example, Patent Document 1). [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent Publication No. 2021-002791 Summary of the Invention [Problem to be solved by the invention]

[0005] To measure flow rates, float observations are performed manually. However, this can be dangerous when the river is flooded. Therefore, it would be desirable to be able to determine the float's speed using, for example, video footage of the float as it flows through the river.

[0006] In one aspect, the present invention aims to determine the speed of a float moving through a river using video. [Means for solving the problem]

[0007] An information processing device according to one aspect of the present invention includes: a setting unit that sets a measurement line representing the height of the water surface of a river based on a position where a line segment representing a side wall of the river at a predetermined distance from a photographing device intersects with the water surface of the river in a frame image of a video of the river photographed by the photographing device; Detecting a detection object corresponding to the position of the float from the video, and excluding, from the detection objects detected from the video, detection objects whose movement trajectories detected from the video satisfy predetermined conditions; The measurement line is used as at least one of a start measurement line and an end measurement line for measuring the flow velocity by a float flowing in the river, The remaining detection targets are A specified section from the start measurement line to the end measurement line The time it takes to travel a given distance Travel time of the float as The apparatus includes a measuring unit that measures the flow rate of a river and a determining unit that determines the flow rate of the river using the travel time and the length of a predetermined section.

[0008] The video can be used to determine the speed at which a float moves through a river. [Brief explanation of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram illustrating a measurement system according to an embodiment. [Figure 2] FIG. 10 is a diagram illustrating an example of a display screen displaying a video of a river for which a flow rate is to be determined. [Figure 3] 1A and 1B are diagrams illustrating detection targets according to an embodiment. [Figure 4] 10A and 10B are diagrams illustrating an example of setting a measurement line according to the position of the water surface according to the embodiment. [Figure 5] FIG. 10 is a diagram illustrating a measurement line at a second distance according to the embodiment. [Figure 6] 10A and 10B are diagrams illustrating measurement of a movement time of a detection object from a start measurement line to an end measurement line according to an embodiment. [Figure 7] 10A and 10B are diagrams illustrating measurement of a travel time of a detection object from a start measurement line to an end measurement line according to the embodiment; [Figure 8] FIG. 2 is a diagram illustrating a detection region according to the embodiment. [Figure 9] FIG. 10 is a diagram illustrating an example of an operation flow of a measurement process according to the embodiment. [Figure 10]FIG. 1 is a diagram illustrating an example of a hardware configuration of a computer for realizing an information processing device according to an embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0010] Hereinafter, several embodiments of the present invention will be described in detail with reference to the drawings. Note that the same reference numerals are used to designate corresponding elements in the various drawings.

[0011] FIG. 1 is a diagram illustrating a measurement system 100 according to an embodiment. The measurement system 100 may include, for example, an information processing device 101 and an image capturing device 102. The information processing device 101 may be, for example, a computer such as a server computer, a personal computer (PC), a mobile PC, or a tablet terminal. The image capturing device 102 may be, for example, a device that captures video, such as a camera. The image capturing device 102 may be installed facing the direction in which the river flows so as to capture the river. Note that in another embodiment, the image capturing device 102 may be installed in another orientation, and in one example, may be installed facing upstream along the river.

[0012] In one example, the information processing device 101 and the image capturing device 102 may be communicatively connected. For example, the information processing device 101 and the image capturing device 102 may be connected by wire or wirelessly, or in another example, may be connected via a network. In another example, the information processing device 101 may acquire a video captured by the image capturing device 102 via a storage medium.

[0013] The information processing device 101 also includes, for example, a control unit 110, a storage unit 120, and a communication unit 130. The control unit 110 includes, for example, a setting unit 111, a measurement unit 112, and a determination unit 113, and may also include other functional units. The storage unit 120 of the information processing device 101 stores information such as video data of a float floating in a river. The communication unit 130 communicates with other devices such as the imaging device 102 in accordance with instructions from the control unit 110. Details of each of these units and further details of the information stored in the storage unit 120 will be described later.

[0014] Fig. 2 is a diagram illustrating a display screen 200 that displays a video of a river 201 for which a flow rate is to be determined. The display screen 200 in Fig. 2 includes the river 201. As shown in Fig. 2, the imaging device 102 may be installed, for example, facing in the direction in which the river 201 flows so as to capture the river 201.

[0015] In this embodiment, to determine the flow rate of the river 201, a float flowing in the river 201 is photographed, and the water level and the time it takes for the float to pass through a predetermined section are identified from the video. Note that the time it takes for the float to pass through a predetermined section from the video may represent the flow velocity. In this embodiment, the flow rate is determined from the time it takes for the float to pass through the predetermined section identified from the video and the cross-sectional area of the river identified from the water level.

[0016] Therefore, according to the embodiment, it is possible to reduce the number of personnel and labor required for measuring flow rate. Also, since it is not necessary to deploy observers to observe floats when the water level rises, it is possible to reduce the risk of observers being exposed to danger. The embodiment will be described in more detail below.

[0017] 3A and 3B are diagrams illustrating an example of a detection object 300 according to an embodiment. FIG. 3A illustrates a float 301. The float 301 may have a structure that allows it to float on the water surface when flowing in a river, for example. Furthermore, the float 301 may have a shape that is easy to detect using a recognition model generated by machine learning or the like. The control unit 110 of the information processing device 101 may then detect the float 301 as the detection object 300 from a video, for example.

[0018] In one embodiment, an additional structure may be attached to the float 301. For example, if the float 301 is floated alone in a river, the float 301 may be hidden among the waves. Therefore, in one embodiment, a balloon 302 may be attached to the float 301 to make it easier to measure the position of the float 301. FIG. 3( b) shows an example in which the balloon 302 is attached to the float 301. In this case, the control unit 110 of the information processing device 101 may, for example, detect the float 301 and the balloon 302 as the detection object 300 from a video. Alternatively, the control unit 110 of the information processing device 101 may, for example, detect the balloon 302 attached to the float 301 as the detection object 300 from a video. The detection object 300 may correspond to the position of the float 301, and the position of the detection object 300 may be used instead of the position of the float 301. The following describes an example in which the balloon 302 is detected as the detection object 300 from a video.

[0019] In the embodiment, the measurement line is set according to the position of the water surface. Setting of the measurement line according to the position of the water surface according to the embodiment will be described below.

[0020] FIG. 4 is a diagram illustrating an example of setting a measurement line according to the position of the water surface according to an embodiment. For example, on a slope that forms the side wall of a river 201 shown in an image, a line segment 401 is drawn at a position that is approximately a predetermined distance from the image capture device 102. This line segment 401 may represent, for example, the side wall of the river 201. In one example, the line segment 401 representing the side wall of the river 201 may be a straight line as shown in FIG. 4. However, the embodiment is not limited to this. For example, in another embodiment, the line segment 401 representing the side wall of the river 201 may be a curve that follows the shape of the side wall of the river in a plane at a predetermined distance from the image capture device 102. The line segment 401 may be, for example, a line drawn by a user. Alternatively, for example, a marker or the like may be installed at a predetermined distance from the image capture device 102, and the control unit 110 may detect the installed marker in frame images of a video to identify the position of the line segment 401. In this case, the control unit 110 may generate the line segment 401 based on the position of the marker identified from the frame images of the video.

[0021] The control unit 110 then identifies the position of a measurement line 402 representing the water surface height at the position where the line segment 401 intersects with the water surface of the river. In FIG. 4, the measurement line 402 is drawn at the position where the line representing the river width intersects with the line segment 401. In the example of FIG. 4, a dashed line parallel to the measurement line 402 is drawn above the measurement line 402, indicating the position of the measurement line 402 when the water level rises. In the example of FIG. 4, a dashed line parallel to the measurement line 402 is drawn below the measurement line 402, indicating the position of the measurement line 402 when the water level drops. The control unit 110 can then draw the measurement line 402, representing the position of the water surface corresponding to the water level at a predetermined distance from the image capture device 102, according to the trapezoid formed by the measurement line 402 and the dashed line, as shown in FIG. 4, for example. In one example, the predetermined distance may be 10 m from the image capture device 102. In addition, the predetermined distance may be referred to as a first distance, in one example.

[0022] In this case, a second distance is set further back on the display screen than the first distance, and similarly, a line segment 501 representing the side wall of the river is drawn at a position the second distance from the image capture device 102, thereby making it possible to draw a measurement line 502 representing the position of the water surface at the second distance. Note that the second distance may be, for example, different from the first distance, and may be farther from the image capture device 102 than the first distance. The second distance may be, for example, 60 m.

[0023] FIG. 5 is a diagram illustrating a measurement line 502 at a second distance according to the embodiment. In FIG. 5, a second trapezoid is shown behind the trapezoid described in FIG. 4, and a measurement line 502 is drawn at a position where a line segment 501 representing the sidewall of the river 201 at the second distance intersects with the river width. As described above, according to the embodiment, the control unit 110 can draw the measurement lines 402 and 502 representing the water surface positions corresponding to two distances for the river 201 shown in the video. Therefore, by letting the detection object 300 flow in the river 201 shown in the video and measuring the time it takes for the detection object 300 to travel the distance from the measurement line 402 to the measurement line 502, it is possible to obtain the time required for the detection object 300 to travel the distance from the measurement line 402 to the measurement line 502. The time taken for the object to be detected 300 to travel the distance from measurement line 402 to measurement line 502 can be used as the time taken for the float 301 to travel from measurement line 402 to measurement line 502, and the flow velocity of the river 201 can be estimated.

[0024] In one example, the first distance may be further upstream of the river than the second distance. In this case, the detection object 300 flows from the first distance measurement line 402 toward the second distance measurement line 502, and the control unit 110 may measure the time it takes for the detection object 300 to flow from the measurement line 402 to the measurement line 502. In the example of FIG. 5, the second distance is longer than the first distance and is located further back, but the embodiment is not limited to this. For example, the back side of the video display screen 200 may be the upstream side of the river. In this case, the second distance may be shorter than the first distance and be located closer to the viewer. In the following embodiment, the measurement line 402 on the upstream side of the river 201 may be referred to as the start measurement line. The measurement line 502 on the downstream side of the river 201 may be referred to as the end measurement line.

[0025] Next, the measurement of the travel time of the float 301 from the start measurement line to the end measurement line will be described. In the following example, the detection object 300 is, for example, a balloon 302 attached to the float 301. In this case, the position of the detection object 300 can be identified by detecting the balloon 302 from the video, and the position of this detection object 300 can be used to indicate the position of the float 301.

[0026] 6 is a diagram illustrating measurement of the travel time of the detection object 300 from the start measurement line 601 to the end measurement line 602 according to the embodiment. In this case, the control unit 110 measures the time it takes for the detection object 300 to travel the distance from the start measurement line 601 to the end measurement line 602 by measuring the time it takes for the detection object 300 to travel the distance from the start measurement line 601 to the end measurement line 602.

[0027] Furthermore, the detection of the detection object 300 from the frame images of the video can be performed by, for example, using an object detection technique using local features. For example, the control unit 110 may detect the detection object 300 from the frame images of the video using a recognition model that has been machine-learned to detect a balloon 302 as the detection object 300.

[0028] In the embodiment, the control unit 110 can specify the trajectory of the detection object 300 using a tracking technique or the like, based on the detection object 300 detected from time-series frame images of the video. The control unit 110 can then acquire the movement time of the detection object 300 from the start measurement line 601 to the end measurement line 602, based on the trajectory of the detection object 300 in the video.

[0029] 7 is a diagram illustrating measurement of travel time from a start measurement line 601 to an end measurement line 602 of the detection object 300 according to the embodiment. As shown in FIG. 7, in one example, the control unit 110 may start measuring time when half of the height of a bounding box set for the detection object 300 detected from a frame image of a video exceeds the start measurement line 601. Furthermore, the control unit 110 may end measurement of time when half of the height of the bounding box set for the detection object 300 exceeds the end measurement line 602, for example. Then, the control unit 110 may obtain the travel time required for the detection object 300 to travel the distance from the start measurement line 601 to the end measurement line 602 from the difference between the start time and the end time of the measurement.

[0030] Furthermore, the positions of the start measurement line 601 and the end measurement line 602 both represent the water level of the river. Therefore, for example, by investigating the shape of the riverbed of the river in advance, the control unit 110 can obtain the cross-sectional area of the river 201 corresponding to the water level at a predetermined position of the river, such as the position of the start measurement line 601 or the position of the end measurement line 602.

[0031] In the embodiment, the control unit 110 may calculate the flow rate of the river from the cross-sectional area of the river 201 and the travel time required for the detection object 300 to travel the distance from the start measurement line 601 to the end measurement line 602. The travel time required for the detection object 300 to travel the distance from the start measurement line 601 to the end measurement line 602 may correspond to the travel speed of the float 301 set afloat in the river 201. In one example, the control unit 110 may use the travel time of the detection object 300 to calculate the flow speed of the river 201.

[0032] As described above, according to the embodiment, the moving speed of the float 301 flowing in the river can be determined from the video. Then, the flow rate can be calculated based on the determined moving speed of the float 301.

[0033] In the above embodiment, an example is described in which a balloon 302 is detected as the detection object 300, but the embodiment is not limited to this. For example, at night, the balloon 302 may be difficult to see due to darkness. Therefore, in one example, the control unit 110 may detect a float 301 illuminated using a chemical light as the detection object 300. For example, the control unit 110 may detect the detection object 300 from a video using a recognition model that has been subjected to machine learning to detect the illuminated float 301 as the detection object 300 from the video. By detecting the illuminated float 301 as the detection object 300 in this way, the control unit 110 can measure the flow rate even at night.

[0034] Incidentally, when detecting the detection object 300 from a video by object detection, for example, something other than the detection object 300 may be detected as the detection object 300, resulting in noise. For example, in the case of nighttime photography, lights from an apartment building, car headlights, etc. may be reflected on the water surface and may be detected as the detection object 300.

[0035] Alternatively, for example, if a whirlpool or the like occurs in a river, the float 301 may be caught in the vortex. In this case, the float 301 may flow backward in the river or be caught in the vortex, and it may take longer to flow than if it were not caught in the vortex, and it may move along a trajectory that is not suitable for measuring the flow velocity of the river.

[0036] Therefore, in the embodiment, if the detected detection object 300 exhibits unnatural movement, the control unit 110 may exclude the detection object 300 from the objects for which travel time is to be measured. For example, the control unit 110 may exclude, as detection objects 300 exhibiting unnatural movement, reverse flow from downstream to upstream, extremely fast movement in which the movement distance per unit time is equal to or greater than a predetermined threshold, extremely slow movement in which the movement distance per unit time is equal to or less than a predetermined threshold, a jagged trajectory, or the like. Alternatively, if the difference between the predicted position of the trajectory based on a trained model that has learned the past behavior of the detection object 300 and the actual detected position is greater than a predetermined threshold, the control unit 110 may exclude the detection object 300 from the objects for which travel time is to be measured.

[0037] As an example, the control unit 110 compares the coordinates of the detection object 300 detected from the video at a first time with the coordinates at a second time later than the first time and determines that the detection object 300 is flowing backward. In this case, the control unit 110 may exclude the detection object 300 from the targets for measuring the travel time and not use the detection object 300 in determining the flow rate. For example, the control unit 110 may detect the backward flow of the detection object 300 when the coordinate position of the detection object 300 is moving upstream.

[0038] Furthermore, for example, if the movement speed of the detected detection object 300 is too fast or too slow, it may be noise. Therefore, in the embodiment, the control unit 110 calculates the movement speed from, for example, the movement distance per unit time of the detected detection object 300. If the movement speed is equal to or greater than a first movement speed, the detection object 300 may be excluded from the movement time measurement targets and not used in determining the flow rate. This makes it possible to exclude extremely fast-moving detection objects 300 as noise. The first movement speed, which represents an extremely fast movement speed, may be, for example, faster than the flow speed of a river, and in one example, may be faster by a predetermined percentage or more than a flow speed representative of a river, such as the average flow speed of the river.

[0039] Furthermore, in the embodiment, the control unit 110 calculates the movement speed from, for example, the movement distance per unit time of the detected detection object 300. If the movement speed is equal to or less than the second movement speed, the detection object 300 may be excluded from the movement time measurement targets and not used in determining the flow rate. Note that the second movement speed may be slower than the first movement speed. This makes it possible to eliminate extremely slow-moving detection objects 300 as noise. The second movement speed, which indicates an extremely slow movement speed, may be, for example, slower than the flow speed of a river, and in one example, may be slower by a predetermined percentage or less than a flow speed representative of a river, such as the average flow speed of the river.

[0040] Furthermore, the float 301 tends not to exhibit a behavior of moving in small, opposite directions, such as zigzag movements relative to the flow of the river. Therefore, when the detected detection object 300 exhibits a zigzag trajectory, the control unit 110 may determine that an object other than the detection object 300 has been erroneously detected, and may exclude the detection object 300 from the objects to be measured for travel time, and may not use the object 300 in determining the flow rate.

[0041] It is also possible to eliminate noise based on the behavior of the detection object 300 specific to the river in question. For example, the control unit 110 may predict the movement of the detection object 300 using a recognition model that has learned the past behavior of the detection object 300 flowing through the river. Then, if the predicted position and the detected position are significantly different from a predetermined condition, the control unit 110 may exclude the detection object 300 from the objects for measuring the travel time.

[0042] For example, the detection object 300 is released into a target river and photographed by the photographing device 102, and a trajectory of the detection object 300 flowing through the target river is generated from the video. The obtained trajectory of the detection object 300 flowing through the river can then be used as training data to train a recognition model that predicts the movement of the detection object 300. The control unit 110 may then predict the movement of the detection object 300 using the recognition model generated in this way, and if the deviation of the actual detected position from the predicted position is greater than or equal to a predetermined threshold, the control unit 110 may reject the detection object 300. This makes it possible to reject noise based on the behavior of the detection object 300 specific to the target river.

[0043] Furthermore, according to an embodiment, the control unit 110 may set a detection area for the detection target object 300 using the determined start measurement line 601 and end measurement line 602. In one example, the control unit 110 may set a rectangular area surrounded by the start measurement line 601 and end measurement line 602 as the detection area 800, as shown in Fig. 8. Furthermore, in another embodiment, the control unit 110 may further detect the width of a river from the video by using a technique such as segmentation AI (artificial intelligence), and set the detection area using the river width.

[0044] Furthermore, the measurement section for measuring the travel time can be set to, for example, any distance from the camera 102. As an example, in rivers managed by the government, sight lines for indicating the bank top height and the like may be installed. Therefore, in one embodiment, the positions of the sight lines may be used to determine the positions of the start measurement line 601 and the end measurement line 602.

[0045] In the above embodiment, an example is described in which both the start measurement line 601 and the end measurement line 602 are determined based on the intersection of the line segment representing the side wall of the river 201 with the water surface, but the embodiment is not limited to this. For example, in another embodiment, one of the start measurement line 601 and the end measurement line 602 may be determined based on the intersection of the line segment representing the side wall of the river 201 with the water surface. In this case, the position of one measurement line may be determined depending on the position of the other measurement line that has been determined.

[0046] 9 is a diagram illustrating an example of an operation flow of measurement processing according to an embodiment. The control unit 110 of the information processing device 101 may start the operation flow of FIG. 9 when, for example, an instruction to execute measurement processing on video data is input.

[0047] In S901, the control unit 110 identifies a measurement line based on, for example, a line segment representing the side wall of a river at a predetermined distance set in the video data and the water surface. For example, as illustrated with reference to FIG. 4, the control unit 110 may identify a measurement line 402 at a position where a line segment 401 at a first distance intersects with the water surface of the river. Note that the measurement line 402 may be, for example, the start measurement line 601.

[0048] 5, the control unit 110 may specify a measurement line 502 at a position where a line segment 501 at the second distance intersects with the water surface of the river. The measurement line 502 may be, for example, an end measurement line 602.

[0049] In another embodiment, the control unit 110 may determine one of the start measurement line 601 and the end measurement line 602 based on, for example, an intersection between a line segment representing the side wall of the river and the water surface. In this case, the control unit 110 may determine the position of one measurement line based on the position of the other measurement line determined based on the intersection between a line segment representing the side wall of the river and the water surface.

[0050] In S902, the control unit 110 sets, for example, a detection area for the detection target object 300. For example, the control unit 110 may set the detection area for detecting the detection target object 300 using the start measurement line 601 and the end measurement line 602, as described in FIG.

[0051] In S903, the control unit 110 may detect the detection object 300 in the frame image of the video. For example, the control unit 110 may detect the detection object 300 by performing object detection on the detection area of the frame image. In one example, the control unit 110 may detect the detection object 300 included in the detection area of the frame image using a recognition model that has been machine-learned to detect the detection object 300. Note that in one example, a bounding box may be set for the detected detection object 300.

[0052] In S904, the control unit 110 tracks the detection object 300 in the video. For example, the control unit 110 may use a tracking technique to identify the trajectory of movement of the detection object 300. In one example, the control unit 110 may identify the trajectory of the detection object 300 by regarding the bounding box that is closest in consecutive frames as the same detection object 300.

[0053] In S905, the control unit 110 may exclude unnecessary detection objects 300 from the detected detection objects 300 based on the trajectories of the respective detection objects 300. For example, the control unit 110 may exclude a detection object 300 when the trajectory of the detection object 300 flows backward upstream. Furthermore, for example, the control unit 110 may exclude a detection object 300 when the trajectory of the detection object 300 moves in a zigzag pattern.

[0054] In S906, the control unit 110 excludes the detection target 300 based on the amount of movement in a predetermined time. For example, the control unit 110 may exclude the detection target 300 if the movement speed of the detection target 300 is too fast or too slow based on the trajectory of the detection target 300.

[0055] In S907, the control unit 110 may, for example, exclude the detection target 300 based on the behavior specific to the target river. For example, the control unit 110 predicts the movement of the detection target 300 using a recognition model generated by machine learning to predict the movement of the detection target 300 flowing through the river. Then, the control unit 110 may exclude, as noise, a detection target whose detected position deviates significantly from the predicted position and satisfies a predetermined condition.

[0056] In S908, the control unit 110 measures, for example, the travel time required for the remaining detection object 300 that was not removed to travel a predetermined distance from the start measurement line 601 to the end measurement line 602. For example, the control unit 110 may determine the time when half the height of the bounding box set for the detection object 300 in the process of S903 exceeds the start measurement line 601 as the start time of the measurement. Furthermore, the control unit 110 may determine the time when half the height of the bounding box set for the detection object 300 in the process of S903 exceeds the end measurement line 602 as the end time of the measurement. Then, the control unit 110 may obtain the travel time required for the detection object 300 to travel the distance from the start measurement line 601 to the end measurement line 602 from the difference between the start time and the end time of the measurement.

[0057] In S909, the control unit 110 measures the flow rate of the river based on the obtained travel times of the remaining detection objects 300, and this operation flow ends. For example, the cross-sectional area of the river can be determined in advance. Note that, for example, the cross-sectional area of the river may be the cross-sectional area obtained when the river is cut by a plane including a direction perpendicular to the flow direction of the river and the vertical direction. Therefore, the control unit 110 may calculate the flow rate of the river from the cross-sectional area of the river at a predetermined position, such as the start measurement line 601 or the end measurement line 602, and the travel time required for the river to flow through the section from the start measurement line 601 to the end measurement line 602.

[0058] As described above, according to the embodiment, the positions of the start measurement line 601 and the end measurement line 602 can be identified as a predetermined section for measuring the travel time of the float 301 in the video captured by the imaging device 102. Then, according to the embodiment, the travel time required for the float 301 to travel through the predetermined section can be identified as the travel time required for the detection object 300 to travel from the start measurement line 601 to the end measurement line 602, which corresponds to the predetermined section.

[0059] Furthermore, according to the embodiment, the flow rate of the river can be calculated from the video captured by the imaging device 102. This reduces the number of personnel required for flow rate measurement. It also reduces the risk of danger to observers who observe floats during times of flooding.

[0060] In the above-described embodiment, an example is shown in which the detection target 300 is excluded based on the trajectory of the movement of the detected detection target 300. In the embodiment, detection targets 300 whose movement speed is too fast or too slow are excluded. Furthermore, an example is shown in which the detection target 300 is excluded based on the behavior of the detection target 300 specific to the target river. For example, by eliminating noise in this manner, it is possible to eliminate detection targets 300 that are not suitable for determining the flow speed of the river. As an example, it is possible to eliminate detection targets 300 that are not suitable for determining the flow speed of the river, such as noise such as light reflected on the water surface or detection targets 300 caught in whirlpools generated in the river. This improves the accuracy of flow speed measurement, thereby improving the accuracy of flow rate measurement.

[0061] Furthermore, according to the embodiment, the flow rate can be determined by processing the video on a computer, which reduces artificial measurement inaccuracies, such as those caused by differences in the observer's level of proficiency. Also, since measurements can be made simply by letting the float 301 float in the river, the workload can be reduced even when performing long-term observations, such as continuous or frequent observations.

[0062] Although the above describes an exemplary embodiment, the embodiment is not limited thereto. For example, the above-described operational flow is an example, and the embodiment is not limited thereto. If possible, the operational flow may be executed by changing the order of processes, may include additional processes, or may omit some processes. For example, the process of setting the detection area in S902 and the processes of excluding the detection target from S905 to S907 in FIG. 9 may be omitted.

[0063] In the above embodiment, in the process of S901, the control unit 110 operates as, for example, the setting unit 111. In addition, in the process of S908, the control unit 110 operates as, for example, the measurement unit 112. In the process of S909, the control unit 110 operates as, for example, the determination unit 113.

[0064] Fig. 10 is a diagram illustrating an example of the hardware configuration of a computer 1000 for realizing an information processing device 101 according to an embodiment. The hardware configuration for realizing the information processing device 101 in Fig. 10 includes, for example, a processor 1001, a memory 1002, a storage device 1003, a reading device 1004, a communication interface 1006, and an input / output interface 1007. The processor 1001, memory 1002, storage device 1003, reading device 1004, communication interface 1006, and input / output interface 1007 are connected to one another via, for example, a bus 1008.

[0065] The processor 1001 may be, for example, a single processor, or a multi-processor or multi-core processor. The processor 1001 provides some or all of the functions of the control unit 110 described above by using the memory 1002 to execute a program that describes the procedures of the above-mentioned operation flow. For example, the processor 1001 of the information processing device 101 operates as the setting unit 111, the measurement unit 112, and the determination unit 113 by reading and executing a program stored in the storage device 1003.

[0066] The memory 1002 is, for example, a semiconductor memory and may include a RAM area and a ROM area. The storage device 1003 is, for example, a semiconductor memory such as a hard disk or flash memory, or an external storage device. RAM is an abbreviation for Random Access Memory. ROM is an abbreviation for Read Only Memory.

[0067] The reading device 1004 accesses the removable storage medium 1005 in accordance with instructions from the processor 1001. The removable storage medium 1005 is realized by, for example, a semiconductor device, a medium that inputs and outputs information by magnetic action, or a medium that inputs and outputs information by optical action. An example of a semiconductor device is a USB (Universal Serial Bus) memory. An example of a medium that inputs and outputs information by magnetic action is a magnetic disk. An example of a medium that inputs and outputs information by optical action is a CD-ROM, DVD, Blu-ray Disc, etc. (Blu-ray is a registered trademark). CD is an abbreviation for Compact Disc. DVD is an abbreviation for Digital Versatile Disk.

[0068] The storage unit 120 includes, for example, a memory 1002, a storage device 1003, and a removable storage medium 1005. For example, the storage device 1003 of the information processing device 101 stores video data of a float 301 floating in a river.

[0069] The communication interface 1006 communicates with other devices according to instructions from the processor 1001 .

[0070] The input / output interface 1007 may be, for example, an interface between an input device and an output device. The input device is, for example, a device such as a keyboard, a mouse, or a touch panel that accepts instructions from a user. The output device is, for example, a display device such as a display, and an audio device such as a speaker.

[0071] Each program according to the embodiment is provided to the information processing device 101 in the following form, for example. (1) It is pre-installed in the storage device 1003. (2) Provided by removable storage medium 1005. (3) Provided from a server such as a program server.

[0072] The hardware configuration of the computer 1000 for realizing the information processing device 101 described with reference to FIG. 10 is an example, and the embodiment is not limited thereto. For example, part of the above-described configuration may be deleted, or new configuration may be added. In another embodiment, for example, part or all of the functions of the above-described control unit 110 may be implemented as hardware using an FPGA, SoC, ASIC, PLD, or the like. Note that FPGA is an abbreviation for Field Programmable Gate Array. SoC is an abbreviation for System-on-a-chip. ASIC is an abbreviation for Application Specific Integrated Circuit. PLD is an abbreviation for Programmable Logic Device.

[0073] Several embodiments have been described above. However, the embodiments are not limited to the above embodiments and should be understood to include various modifications and alternative forms of the above embodiments. For example, it will be understood that the various embodiments can be realized by modifying the components without departing from the spirit and scope of the embodiments. It will also be understood that various embodiments can be implemented by appropriately combining multiple components disclosed in the above-described embodiments. Furthermore, it will be understood by those skilled in the art that various embodiments can be implemented by deleting some components from all the components shown in the embodiments or by adding some components to the components shown in the embodiments. [Explanation of symbols]

[0074] 100: Measurement system 101: Information processing device 102: Imaging device 110: Control unit 111: Settings section 112: Measurement section 113: Decision section 120: Storage section 130: Communications Department 200:Display screen 201: River 300: Object to be detected 301: Float 302: Balloon 1000: Computer 1001: Processor 1002: Memory 1003 :Storage device 1004: Reading device 1005: Removable storage media 1006: Communication interface 1007: Input / output interface 1008: Bus

Claims

1. a measurement line representing the height of the water surface of the river is set based on a position where a line segment representing a side wall of the river at a predetermined distance from a photographing device intersects with the water surface of the river in a frame image of a video photographed of the river by the photographing device; Detecting a detection target corresponding to the position of the float from the video; Among the detection objects detected from the video, those detection objects whose movement trajectories detected from the video satisfy a predetermined condition are excluded; The measurement line is used as at least one of a start measurement line and an end measurement line for measuring the flow velocity of a float flowing in the river, and the time required for the remaining detection objects to move through a predetermined section from the start measurement line to the end measurement line is measured as the travel time of the float flowing through the predetermined section; determining the flow rate of the river using the travel time and the length of the predetermined section; A measurement program that causes an information processing device to execute the process.

2. Among the detection objects detected from the video, the trajectory of the movement of the detection object detected from the video excludes the detection object whose movement includes movement toward the upstream side of the river. The measurement program according to claim 1 .

3. Among the detection objects detected from the video, those detection objects whose movement speed is equal to or greater than a first movement speed are excluded based on the trajectory of the movement of the detection objects detected from the video. The measurement program according to claim 1 .

4. Among the detection objects detected from the video, those whose movement speed is equal to or less than a second movement speed are excluded based on the trajectory of the movement of the detection objects detected from the video. The measurement program according to claim 1 .

5. Among the detected objects detected from the video, those detected objects whose deviation from the predicted position of the detected object according to a trained model that has been machine-learned to predict the movement of the detected object in the river is large enough to satisfy predetermined conditions are excluded. The measurement program according to claim 1 .

6. A measurement method executed by an information processing device, the information processing device comprising: a measurement line representing the height of the water surface of the river is set based on a position where a line segment representing a side wall of the river at a predetermined distance from a photographing device intersects with the water surface of the river in a frame image of a video photographed of the river by the photographing device; Detecting a detection target corresponding to the position of the float from the video; Among the detection objects detected from the video, those detection objects whose movement trajectories detected from the video satisfy a predetermined condition are excluded; The measurement line is used as at least one of a start measurement line and an end measurement line for measuring the flow velocity of a float flowing in the river, and the time required for the remaining detection objects to move through a predetermined section from the start measurement line to the end measurement line is measured as the travel time of the float flowing through the predetermined section; determining the flow rate of the river using the travel time and the length of the predetermined section; A measuring method comprising:

7. a setting unit that sets a measurement line representing the height of the water surface of the river based on a position where a line segment representing a side wall of the river at a predetermined distance from a photographing device intersects with the water surface of the river in a frame image of a video of the river photographed by the photographing device; a measuring unit that detects from the video an object to be detected that corresponds to the position of the float, excludes from the video an object whose movement trajectory satisfies a predetermined condition, uses the measurement line as at least one of a start measurement line and an end measurement line for measuring the flow velocity of a float flowing through the river, and measures the time it takes for the remaining object to move through a predetermined section from the start measurement line to the end measurement line as the movement time of the float flowing through the predetermined section; a determination unit that determines the flow rate of the river using the travel time and the length of the predetermined section; An information processing device comprising:

Images