JP2015041188A - Image analyzing device and image analyzing method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a technology that allows an inspector to easily confirm whether or not a camera is normal, which is used in measurement of a traveling state of a vehicle.SOLUTION: There is provided an image analyzing device 20 that outputs analysis data obtained by analyzing an image photographed by an imaging unit 170, and includes a display control unit 213 that displays, when a result of measurement conducted on the basis of the current image in which a plane on the road is photographed by the imaging unit 170 is determined to be abnormal, an abnormal candidate image and a reference image in which the plane of the road is photographed in advance by the imaging unit 170.

Description

  The present invention relates to an image analysis apparatus and an image analysis method.

  2. Description of the Related Art In recent years, a technique has been developed for measuring the traveling state of a vehicle from a captured image obtained by capturing a road plane with a camera. Examples of the running situation of the vehicle include traffic volume and vehicle speed. If an abnormality occurs in the camera while measuring the traveling state of the vehicle, a situation may occur in which the measurement result of the traveling state of the vehicle also becomes abnormal. As an example, the measurement result may be abnormal when the imaging range of the camera is out of the normal range.

  Various techniques have been disclosed as techniques for detecting camera abnormalities. For example, there is disclosed a technique for determining that another camera is abnormal when the installation position of another camera shown in a captured image captured by a camera exceeds a normal range (for example, a patent) Reference 1).

JP 2011-76573 A

However, when the technique described in Patent Document 1 is used, it is necessary to install a camera so that another camera appears in the captured image. It is difficult. In order to confirm whether the camera is normal, the inspector generally inspects the captured image or directly inspects the camera. Therefore, the inspector determines whether the camera is normal. Can not be easily confirmed.
When the technique described in Patent Document 1 is used, it is necessary to install a camera so that another camera appears in the captured image. It cannot be applied when using a camera that does not show the camera.
In order to confirm whether or not the camera is normal, the inspector generally inspects the captured image or directly inspects the camera. In the technique described in Patent Document 1, it is necessary for an inspector to constantly check whether there is an abnormality in the camera. In addition, the determination of whether or not the camera is abnormal is based on a single image that is currently being taken and is made by visual observation, so that it depends on the experience of the inspector and is likely to cause blurring and error. Furthermore, even when the inspector determines that the camera is abnormal, there are cases where the measurement is not affected.

Accordingly, the present invention has been made in view of the above problems, and an object of the present invention is to easily confirm with an inspector whether or not a camera used for measurement of a running state of a vehicle is normal. It is to provide a technique that can be performed.
Therefore, the present invention has been made in view of the above problems, and an object of the present invention is to determine whether or not a camera used for measurement of the traveling state of a vehicle is normal. It is an object of the present invention to provide a technique that allows an inspector to check at a timing and to make it easier and more accurate.

  In order to solve the above problem, according to an aspect of the present invention, there is provided an image analysis apparatus that outputs analysis data obtained by analyzing an image captured by a predetermined imaging unit, and a road plane is generated by the predetermined imaging unit. A display for displaying a reference image in which the road plane is captured in advance by the predetermined imaging unit and a predetermined abnormality candidate image when it is determined that the measurement result measured based on the captured current image is abnormal An image analysis apparatus including a control unit is provided.

  The measurement result may include at least one of current traffic volume and current vehicle speed.

  The image analysis apparatus may further include a determination unit that determines whether or not the measurement result is abnormal.

  The determination unit may determine whether or not the current traffic volume is abnormal based on a relationship between the current traffic volume and the old traffic volume measured in the past.

  The determination unit may determine whether or not the current vehicle speed is abnormal based on a relationship between the current vehicle speed and an old vehicle speed measured in the past.

  The determination unit determines that the current traffic volume is abnormal based on a relationship between the current traffic volume and a traffic volume measured based on a captured image captured by another imaging unit adjacent to the predetermined imaging unit. It may be determined whether or not there is.

  If it is determined that the measurement result is abnormal, the display control unit determines whether to display the reference image and the abnormal candidate image based on a comparison result between the reference image and the current image. You may judge.

  When it is determined that the measurement result is abnormal, the display control unit, based on a comparison result between a road plane parameter calculated from the reference image and a road plane parameter calculated from the current image, It may be determined whether to display an image and the abnormality candidate image.

  The display control unit, when it is determined that the measurement result is abnormal, the road information according to the road plane parameter calculated from the reference image and the road according to the road plane parameter calculated from the abnormality candidate image At least one of the information may be displayed.

  The display control unit may superimpose and display the reference image and the abnormality candidate image.

  According to another aspect of the present invention, there is provided an image analysis method for outputting analysis data obtained by analyzing an image captured by a predetermined imaging unit, wherein the current image obtained by capturing a road plane by the predetermined imaging unit is used. An image analysis method including a step of displaying a reference image in which the road plane is captured in advance by the predetermined imaging unit and a predetermined abnormality candidate image when it is determined that the measurement result measured based on the abnormality is abnormal Is provided.

  As described above, according to the present invention, it is possible to make an inspector easily check whether or not a camera used for measurement of a traveling state of a vehicle is normal.

It is a figure for demonstrating the outline | summary of embodiment of this invention. It is a figure which shows the function structural example of the traffic measuring device which concerns on embodiment of this invention. It is a figure which shows the function structural example of the image analyzer which concerns on embodiment of this invention. It is a figure which shows the example of the parameter used by the setting part. It is a figure for demonstrating the example of the function of a setting part. It is a flowchart which shows the operation example of a measurement part and an output control part. It is a flowchart which shows the operation example of the image analyzer which concerns on embodiment of this invention. It is a flowchart which shows the 1st determination example by a determination part. It is a flowchart which shows the 2nd determination example by a determination part. It is a figure for demonstrating the 3rd determination example by the determination part. It is a figure for demonstrating the 3rd determination example by the determination part. It is a figure for demonstrating the modification of the 3rd determination example by the determination part. It is a figure which shows the example of the 1st screen display-controlled by a display control part. It is a figure which shows the example of the 2nd screen display-controlled by a display control part.

  Exemplary embodiments of the present invention will be described below in detail with reference to the accompanying drawings. In the present specification and drawings, components having substantially the same functional configuration are denoted by the same reference numerals, and redundant description is omitted.

  In the present specification and drawings, a plurality of constituent elements having substantially the same functional configuration may be distinguished by attaching different alphabets or numbers after the same reference numeral. However, when it is not necessary to particularly distinguish each of a plurality of constituent elements having substantially the same functional configuration, only the same reference numerals are given.

[Description of overview]
Subsequently, an outline of an embodiment of the present invention will be described. FIG. 1 is a diagram for explaining an outline of an embodiment of the present invention. As shown in FIG. 1, the traffic measurement system 1 and the road plane exist in real space. The traffic measurement system 1 has at least a traffic measurement device 10 and an image analysis device 20, and an imaging unit is incorporated in the traffic measurement device 10. The traffic volume measuring device 10 incorporating the imaging unit is installed in a state where the imaging direction is directed to the road plane. The captured image Img ′ captured by the traffic measuring device 10 shows the boundary line of the lane provided on the road. Further, as shown in FIG. 1, the center of the lens of the traffic measuring device 10 is set to the origin O.

  FIG. 1 shows an example in which an imaging unit is incorporated in the traffic measurement device 10, but the imaging unit is not incorporated in the traffic measurement device 10 and is installed outside the traffic measurement device 10. It may be. In such a case, for example, the traffic measurement device 10 may acquire the captured image Img ′ by receiving the captured image Img ′ transmitted from the imaging unit. Further, for example, the traffic volume measuring device 10 may acquire the captured image Img ′ by reading the captured image Img ′ recorded on the recording medium.

  The captured image captured by the imaging unit incorporated in the traffic measuring device 10 is provided to the image analysis device 20 via the network 30. When the captured image provided to the image analysis device 20 is analyzed by the image analysis device 20, analysis data obtained by the analysis is output from the image analysis device 20. In the example illustrated in FIG. 1, the traffic volume measurement system 1 includes one image analysis device 20, but may include a plurality of image analysis devices 20.

  In the present specification, an example in which analysis data is output by a display unit provided in the image analysis apparatus 20 will be mainly described. However, the analysis data is output to a display unit existing outside the image analysis apparatus 20. Also good. Alternatively, when a monitoring device that monitors the image analysis device 20 is connected to the network 30, the analysis data is output to the monitoring device by the image analysis device 20 via the network 30, and the monitoring device displays the analysis data. Good.

  On the other hand, the traffic volume measuring device 10 measures the traveling state of the vehicle from the captured image. However, when an abnormality occurs in the imaging unit incorporated in the traffic measurement device 10, a situation may occur in which the measurement result of the traveling state of the vehicle also becomes abnormal. As an example, the measurement result may be abnormal when the imaging range of the camera is out of the normal range. However, in general, in order to confirm whether or not the imaging unit is normal, it is necessary for the inspector to inspect the captured image or directly inspect the state of the imaging unit. Therefore, in general, the inspector cannot easily confirm whether or not the imaging unit is normal.

  In view of this, the present specification proposes a technique that allows an inspector to easily check whether or not an imaging unit used for measurement of a traveling state of a vehicle is normal.

  The outline of the embodiment of the present invention has been described above.

[Details of the embodiment]
Next, details of the embodiment of the present invention will be described. First, the functional configuration of the traffic volume measuring device 10 according to the embodiment of the present invention will be described. FIG. 2 is a diagram illustrating a functional configuration example of the traffic volume measuring device 10 according to the embodiment of the present invention. As shown in FIG. 2, the traffic volume measuring device 10 according to the embodiment of the present invention includes a control unit 110, an imaging unit 170, a storage unit 180, and an output unit 190.

  The control unit 110 has a function of controlling the entire operation of the traffic volume measuring device 10. The imaging unit 170 has a function of acquiring a captured image by imaging a real space, and is configured by, for example, a monocular camera. The storage unit 180 can store a program and data for operating the control unit 110. In addition, the storage unit 180 can temporarily store various data necessary in the course of the operation of the control unit 110. The output unit 190 has a function of performing output in accordance with control by the control unit 110. The type of the output unit 190 is not particularly limited, and may be a display device or an audio output device.

  In the example illustrated in FIG. 2, the imaging unit 170, the storage unit 180, and the output unit 190 exist inside the traffic measurement device 10, but all or one of the imaging unit 170, the storage unit 180, and the output unit 190. The unit may be provided outside the traffic measurement device 10. The control unit 110 includes a setting unit 111, a measurement unit 112, and an output control unit 113. Details of these functional units included in the control unit 110 will be described later.

  The functional configuration example of the traffic volume measuring device 10 according to the embodiment of the present invention has been described above.

  Subsequently, a functional configuration of the image analysis apparatus 20 according to the embodiment of the present invention will be described. FIG. 3 is a diagram illustrating a functional configuration example of the image analysis apparatus 20 according to the embodiment of the present invention. As shown in FIG. 3, the image analysis apparatus 20 according to the embodiment of the present invention includes a control unit 210, an input unit 270, a storage unit 280, and a display unit 290.

  The control unit 210 has a function of controlling the entire operation of the image analysis apparatus 20. The input unit 270 has a function of receiving an operation input from the user. The storage unit 280 can store a program and data for operating the control unit 210. In addition, the storage unit 280 can temporarily store various data necessary in the course of the operation of the control unit 210. The display unit 290 has a function of performing display according to control by the control unit 210.

  In the example illustrated in FIG. 3, the input unit 270, the storage unit 280, and the display unit 290 exist inside the image analysis apparatus 20, but all or part of the input unit 270, the storage unit 280, and the display unit 290. May be provided outside the image analyzer 20. In addition, the control unit 210 includes an information acquisition unit 211, a determination unit 212, and a display control unit 213. Details of these functional units included in the control unit 210 will be described later.

  The functional configuration example of the image analysis apparatus 20 according to the embodiment of the present invention has been described above.

  Subsequently, details of the functions of the traffic measurement device 10 and the image analysis device 20 will be described. First, calibration can be performed by the traffic measurement device 10 according to the embodiment of the present invention. More specifically, a process for calculating a road plane formula (hereinafter also referred to as a “road plane type”) and a process for calculating the traveling direction of the vehicle may be performed as calibration. Hereinafter, calibration that can be performed by the setting unit 111 will be described with reference to FIGS. 4 and 5.

  FIG. 4 is a diagram illustrating parameters used by the setting unit 111. The setting unit 111 first determines the size pix_dot of the captured image Img ′ per unit pixel of the image sensor based on the size of the image sensor that constitutes the image capture unit 170 and the size of the captured image Img ′ provided to the control unit 110. As a parameter. The captured image Img ′ is generated based on the captured image Img captured on the imaging surface of the image sensor that is separated from the origin O by the focal length. In addition, the captured image Img ′ provided to the control unit 110 can be used by the setting unit 111.

  As shown in FIG. 4, here, a case where the image pickup device is a CCD (Charge Coupled Device) will be described as an example, but the CCD is only an example of the image pickup device. Therefore, the imaging element may be a CMOS (Complementary Metal Oxide Semiconductor) or the like.

  Here, assuming that the CCD size is ccd_size and the size of the captured image Img ′ (horizontal: width × vertical: height) is img_size, the setting unit 111 can calculate pix_dot by the following (Equation 1). In general, since the CCD size is represented by the length of the diagonal line of the CCD, the CCD size is divided by the square root of the sum of squares in the vertical and horizontal directions of the captured image Img ′ as shown in (Equation 1). Is calculated by However, the calculation of the parameter pix_dot by such a method is only an example, and the parameter pix_dot may be calculated by another method. For example, the vertical or horizontal length of the CCD may be used instead of the diagonal line of the CCD.

  Note that the CCD size is easily acquired from the imaging unit 170, for example. Further, the size of the captured image Img ′ is acquired from the storage unit 180, for example. Therefore, the control unit 110 determines, based on these sizes, the three-dimensional coordinates in the real space of the captured image Img captured on the imaging surface of the CCD and the two-dimensional coordinates of the captured image Img ′ provided to the control unit 110. The correspondence can be grasped. That is, the control unit 110 grasps the three-dimensional coordinates in the real space of the captured image Img imaged on the imaging surface of the CCD from the two-dimensional coordinates of the captured image Img ′ provided to the control unit 110 based on this correspondence. can do.

  Calibration can be performed using the parameters thus calculated. Hereinafter, calibration performed by the setting unit 111 using parameters will be described with reference to FIG.

  FIG. 5 is a diagram for explaining the function of the setting unit 111. As shown in FIG. 5, an xyz coordinate system (real space) with the origin O as a reference is assumed. In this xyz coordinate system, the road plane expression is R1x + R2x + R3z + R4 = 0. Further, a traveling direction vector v that is a vector indicating the traveling direction of the vehicle is defined as (vx, vy, vz). In the following description, as shown in FIG. 5, a point (focal point) that is separated from the origin O by the focal length f is set on the y axis, and a plane that passes through this focal point and is perpendicular to the y axis is defined as an imaging surface. The description will be continued assuming that the captured image Img is captured on the imaging surface, but the setting of each coordinate axis is not limited to such an example.

  Two parallel straight lines are drawn in advance on the road plane. Therefore, the parallel two straight lines are shown in the captured image Img. On the road plane, two points Q1 and Q2 that are separated by a known size Q_dis are drawn in advance. In the captured image Img, two points Q1 and Q2 are displayed as Q1 '(xs1, f, zs1) and Q2' (xs2, f, zs2). In the example shown in FIG. 5, Q1 and Q2 are drawn as points on each of two parallel straight lines on the road plane. However, Q1 and Q2 are not particularly limited as long as they are points on the road plane. Not.

  Of the two straight lines shown in the captured image Img, the two points through which the first straight line passes are T1 (x1, y1, z1) and T4 (x4, y4, z4), and the two points through which the second straight line passes are T2. Let (x2, y2, z2) and T3 (x3, y3, z3). Then, as shown in FIG. 5, the coordinates of the intersection of the straight line connecting each of T1, T2, T3 and T4 and the origin O and the road plane are t1 · T1, t2 · T2, t3 · T3 and t4 · T4. It is expressed. For example, the setting unit 111 can perform calibration based on the following (Precondition 1).

(Prerequisite 1)
(Condition 1) The direction vectors of two parallel straight lines on the road plane are the same.
(Condition 2) The roll of the imaging unit 170 is zero.
(Condition 3) The distance from the origin O to the road plane is the height H.
(Condition 4) Q1 and Q2 that are Q_dis apart exist on the road plane.
Note that the roll being 0 means that the imaging unit 170 is installed so that an object installed in a direction perpendicular to the road plane is reflected in the vertical direction on the captured image Img. .

  The setting unit 111 can derive the relational expressions shown in the following (Equation 2) and (Equation 3) based on the various data acquired as described above and (Condition 1).

  Further, the setting unit 111 can derive a relational expression represented by the following (Expression 4) based on the various data acquired as described above and (Condition 2). If the roll is in the 0 state, the perpendicular component to the road plane in the axial direction parallel to the road plane formula (in the example shown in FIG. 5, the x-axis direction) is 0, so the calculation formula is simplified. (For example, if the perpendicular component in the x-axis direction is 0, R1 = 0 can be calculated).

  Further, the setting unit 111 can derive a relational expression represented by the following (Formula 5) based on the various data acquired as described above and (Condition 3).

  Further, the setting unit 111 can derive the relational expressions shown in the following (Expression 6) and (Expression 7) based on the various data acquired as described above and (Condition 4).

  Here, in K1, the distance from the origin O to Q1 (xr1, yr1, zr1) on the road plane is a multiple of the distance from the origin O to Q1 ′ (xs1, f, zs1) on the captured image Img. It is a value indicating whether or not Similarly, in K2, the distance from the origin O to Q2 (xr2, yr2, zr2) on the road plane is a multiple of the distance from the origin O to Q2 ′ (xs2, f, zs2) on the captured image Img. It is a value indicating whether or not Therefore, the relational expression shown in the following (Formula 8) can be derived.

  The setting unit 111 can calculate the measured value Q_dis ′ of the distance between two points (Q1 and Q2) on the road plane from the relational expression shown in (Formula 8) by the following (Formula 9).

  The setting unit 111 can calculate R1, R2, R3, and R4 when the difference between the measured value Q_dis ′ and the known magnitude Q_dis is smallest based on (Equation 1) to (Equation 9). . By calculating R1, R2, R3 and R4 in this way, the road plane formula R1x + R2x + R3z + R4 = 0 is determined.

  The road plane calculation method described above is merely an example. Therefore, the setting unit 111 can also calculate the road plane equation by another method. For example, if the distance between two parallel straight lines on the road plane is known, the road plane formula is calculated without using (Condition 2) by using the distance between the two parallel straight lines on the road plane. be able to.

  The setting unit 111 can also calculate a traveling direction vector v (vx, vy, vz). More specifically, the setting unit 111 can calculate the traveling direction vector v by calculating the direction of at least one of two parallel straight lines on the road plane. For example, the setting unit 111 may calculate the difference between the coordinates t2 · T2 and the coordinates t3 · T3 as the traveling direction vector v, or the difference between the coordinates t1 · T1 and the coordinates t4 · T4 as the traveling direction vector v. It may be calculated.

  The setting unit 111 can perform calibration by the method described above. The road plane equation R1x + R2x + R3z + R4 = 0 and the traveling direction vector v (vx, vy, vz) calculated by such calibration can be used for measuring the traffic volume and the vehicle speed. Further, the road plane type R1x + R2x + R3z + R4 = 0 and the traveling direction vector v (vx, vy, vz) may be used by the image analysis device 20.

  Further, as illustrated in FIG. 5, the setting unit 111 may set a measurement range E1. If it does so, traffic volume may be measured based on the vehicle area | region extracted from the measurement range E1. For example, the setting unit 111 may set the measurement range E1 based on the input operation, or may automatically set the measurement range E1 based on the traveling direction vector v (vx, vy, vz). However, when the imaging range itself is the measurement range, the measurement range need not be set. Below, in order to demonstrate easily, the case where the imaging range itself is made into a measurement range is mainly demonstrated. The output control unit 113 may cause the output unit 190 to output various information set by the setting unit 111.

  The calibration performed by the setting unit 111 has been described above.

  Next, functions of the measurement unit 112 and the output control unit 113 will be described. FIG. 6 is a flowchart illustrating an operation example of the measurement unit 112 and the output control unit 113. First, the measurement unit 112 acquires a reference image (step S11). The reference image is not particularly limited as long as it is an image in which a road plane is previously captured by the imaging unit 170. For example, the vehicle may not be reflected in the reference image, or the vehicle may be reflected.

  Also, the timing at which the reference image is captured is not particularly limited, and the reference image may be an image captured at the time of installing the imaging unit 170, or the latest imaging when imaging is performed every predetermined time. It may be an image updated by an image. Alternatively, the reference image may be a composite image in which a plurality of images in which a road plane is captured in advance by the imaging unit 170 are combined. The output control unit 113 provides the reference image to the image analysis device 20 (step S12).

  Subsequently, the measurement unit 112 measures the traveling state of the vehicle on the road plane based on the current image currently captured by the imaging unit 170 (step S13). The driving situation of the vehicle is not particularly limited, and may be the current traffic volume indicating the current traffic volume, the current vehicle speed indicating the current vehicle speed, or another driving situation. Good. The measurement result obtained by the measurement unit 112 may include at least one of the current traffic volume and the current vehicle speed.

  The traffic measurement method is not particularly limited. For example, the measurement unit 112 measures the traffic volume by extracting the vehicle silhouette area from the current image based on the background difference method, and counting the number of the vehicle silhouette areas that have passed through the imaging range while tracking the vehicle silhouette area. Alternatively, the traffic volume may be measured by other methods.

  Further, the vehicle speed measurement method is not particularly limited. For example, the measurement unit 112 replaces the movement of the vehicle shown in the current image with the movement of the vehicle on the road plane in the real space using the road plane formula, and then the movement amount per unit time on the road plane in the real space. May be measured as the vehicle speed, or the vehicle speed may be measured by other methods. The output control unit 113 provides the current image and the measurement result to the image analysis device 20 (step S14).

  When the operation is continued (“No” in Step S15), the control unit 110 shifts the operation to Step S13, but when the operation is finished (“No” in Step S15), the operation ends. .

  The functions of the measurement unit 112 and the output control unit 113 have been described above.

  Subsequently, an operation example of the image analysis apparatus 20 according to the embodiment of the present invention will be described. FIG. 7 is a flowchart showing an operation example of the image analysis apparatus 20 according to the embodiment of the present invention. Note that the flowchart shown in FIG. 7 only shows an example of the operation of the image analysis apparatus 20. Therefore, the operation of the image analysis apparatus 20 is not limited to the operation example shown by the flowchart of FIG.

  As illustrated in FIG. 7, the information acquisition unit 211 acquires a reference image from the traffic measurement device 10 (step S21). Subsequently, the information acquisition unit 211 acquires the measurement result and the current image from the traffic measurement device 10 (step S22), and the determination unit 212 determines whether the measurement result is abnormal (step S23). . The determination of whether or not the measurement result is abnormal is not particularly limited, but a specific example will be described later. When it is determined that the measurement result is normal (“No” in step S23), the control unit 210 shifts the operation to step S22.

  On the other hand, when it is determined that the measurement result is abnormal (“Yes” in step S23), the display control unit 213 displays the reference image and the abnormality candidate image on the display unit 290 (step S24). The abnormality candidate image may be an image itself that is determined to have an abnormal measurement result by the determination unit 212 or may be captured by the imaging unit 170 after the determination unit 212 determines that the measurement result is abnormal. It may be an image.

  As described above, the display control unit 213 displays the reference image and the abnormality candidate image on the display unit 290, thereby inspecting whether or not the imaging unit used for measuring the traveling state of the vehicle is normal. Can be easily confirmed. Although an example in which the reference image and the abnormality candidate image are displayed on the display unit 290 provided in the image analysis device 20 has been described here, the display control unit 213 is a display unit that exists outside the image analysis device 20. The reference image and the abnormal candidate image may be displayed on 290.

  Alternatively, when the monitoring device is connected to the network 30, the display control unit 213 outputs the reference image and the abnormality candidate image to the monitoring device via the network 30, and the monitoring device outputs the reference image and the abnormality candidate image. It may be displayed. The reference image can be stored in advance in the monitoring device. In such a case, provision of a reference image from the traffic volume measuring device 10 to the image analysis device 20, output of the reference image from the image analysis device 20 to the monitoring device, and the like may be omitted.

  Subsequently, a determination example by the determination unit 212 will be described in more detail. First, the first determination example will be described. FIG. 8 is a flowchart illustrating a first determination example by the determination unit 212. In the first determination example, the current traffic volume is used as an example of the measurement result. Note that the flowchart shown in FIG. 8 merely shows an example of determination by the determination unit 212. Therefore, the determination by the determination unit 212 is not limited to the operation example shown by the flowchart of FIG.

  As illustrated in FIG. 8, the determination unit 212 acquires the current traffic volume acquired by the information acquisition unit 211 (step S31). Subsequently, the determination unit 212 determines whether or not the current traffic volume is abnormal based on the relationship between the current traffic volume and the old traffic volume measured in the past. Specifically, the determination unit 212 may determine whether or not the difference value between the current traffic volume and the old traffic volume measured from the reference image exceeds a threshold value (step S32). The old traffic volume may be measured by the traffic volume measuring device 10 based on the reference image.

  If the difference value exceeds the threshold (“Yes” in step S32), the determination unit 212 may determine that the measurement result is abnormal (step S33). On the other hand, when the difference value does not exceed the threshold value (“No” in step S32), the determination unit 212 may determine that the measurement result is normal (step S34).

  Subsequently, a second determination example will be described. FIG. 9 is a flowchart illustrating a second determination example by the determination unit 212. In the second determination example, the current vehicle speed is used as an example of the measurement result. The flowchart shown in FIG. 9 only shows an example of determination by the determination unit 212. Therefore, the determination by the determination unit 212 is not limited to the operation example shown by the flowchart of FIG.

  As shown in FIG. 9, the determination unit 212 acquires the current vehicle speed acquired by the information acquisition unit 211 (step S41). Subsequently, the determination unit 212 determines whether or not the current vehicle speed is abnormal based on the relationship between the current vehicle speed and the old vehicle speed measured in the past. Specifically, the determination unit 212 may determine whether or not the difference value between the current vehicle speed and the old vehicle speed measured from the reference image exceeds a threshold value (step S42). The old vehicle speed may be measured by the traffic measuring device 10 based on the reference image.

  When the difference value exceeds the threshold value (“Yes” in step S42), the determination unit 212 may determine that the measurement result is abnormal (step S43). On the other hand, when the difference value does not exceed the threshold (“No” in step S42), the determination unit 212 may determine that the measurement result is normal (step S44).

  Subsequently, a third determination example will be described. 10 and 11 are diagrams for explaining a third determination example by the determination unit 212. FIG. In the third determination example, a plurality of traffic volume measuring devices 10 are connected to the network 30. Although FIG. 10 shows the traffic volume measuring devices 10A to 10E as the plurality of traffic volume measuring devices 10 connected to the network 30, the number of the traffic volume measuring devices 10 is not particularly limited. FIG. 10 shows an example in which there are no branch points or junctions on the road.

  As shown in FIG. 10, the traffic volume measuring device 10A and the traffic volume measuring device 10B are adjacent to each other, the traffic volume measuring device 10B and the traffic volume measuring device 10C are adjacent to each other, and the traffic volume measuring device 10C and The traffic measurement device 10D is adjacent, and the traffic measurement device 10D and the traffic measurement device 10E are adjacent. In each of the traffic measurement devices 10A to 10E, a current image in which a road plane is imaged by the imaging unit 170 is acquired.

  Subsequently, in each of the traffic volume measuring devices 10 </ b> A to 10 </ b> E, the current traffic volume is measured by the measurement unit 112, and the current traffic volume is provided to the image analysis device 20 by the output control unit 113. Subsequently, in the image analysis device 20, the current traffic volume provided from each of the traffic volume measuring devices 10A to 10E is acquired by the information acquisition unit 211, and the determination unit 212 determines whether or not the current traffic volume is abnormal. The Here, a case where it is determined whether or not the current traffic volume provided from the traffic volume measuring device 10C is abnormal will be described.

  Specifically, the determination unit 212 determines the current traffic volume provided from the traffic volume measuring device 10C and the current traffic volume provided from the traffic volume measuring device 10B and the traffic volume measuring device 10D adjacent to the traffic volume measuring device 10C. Based on the relationship, it is determined whether or not the current traffic volume provided from the traffic volume measuring device 10C is abnormal. In the following description, the current traffic volume provided from each of the traffic volume measuring devices 10A to 10E may be simply indicated as current traffic volumes a to e. In addition, the points where the imaging units 170 of the traffic volume measuring devices 10A to 10E are installed may be simply indicated as points A to E.

  In the example shown in FIG. 10, since there is no branching point or junction point on the road, the determination unit 212 determines that the current traffic volume c is normal when the current traffic volume b to the current traffic volume d are all equal. It may be determined that On the other hand, if the current traffic volume b and the current traffic volume c are different, and the current traffic volume c and the current traffic volume d are different, the determination unit 212 determines that the current traffic volume b and Whether or not the current traffic volume c is normal may be determined depending on whether or not the current traffic volume d is equal. Specifically, when the current traffic volume b and the current traffic volume d are equal, it may be determined that both the current traffic volume b and the current traffic volume d are normal and the current traffic volume c is abnormal. .

  On the other hand, when the current traffic volume b and the current traffic volume d are different, it is difficult to determine which of the current traffic volume b to the current traffic volume d is abnormal. Therefore, the determination unit 212 is a case where the current traffic volume b and the current traffic volume c are different, and a case where the current traffic volume c and the current traffic volume d are different, and the current traffic volume. If b and the current traffic volume d are different, the current traffic volume a and the current traffic volume e may be further used for the determination.

  For example, the determination unit 212 may determine that the current traffic volume is normal when the current traffic volume exceeding the predetermined number is equal among the current traffic volume a to the current traffic volume e. On the other hand, the determination unit 212 may determine that the remaining current traffic volume is abnormal. The predetermined number is not particularly limited, but may be, for example, half of the current traffic volume. Here, since the number of the current traffic volume is five from the current traffic volume a to the current traffic volume e, the determination unit 212 determines that the current traffic volume is normal if the three current traffic volumes are equal. It may be determined that the remaining current traffic volume is abnormal.

  This will be described with reference to a specific example. In the example illustrated in FIG. 11, the determination unit 212 determines that the current traffic volume “20” at the point B is different from the current traffic volume “90” at the point C, and the current traffic volume “90” at the point C It is determined that the current traffic volume “50” at the point D is different. Therefore, the determination unit 212 determines whether or not the current traffic volume “20” at the point B is equal to the current traffic volume “50” at the point D.

  However, the determination unit 212 determines that the current traffic volume “20” at the point B is different from the current traffic volume “50” at the point D, and the current traffic volume “50” at the point A and the current traffic volume “at the point E”. 50 "is further used for determination. The determination unit 212 may determine that these current traffic volumes are normal because the three current traffic volumes at the points A, D, and E are all equal to “50”. On the other hand, the determination unit 212 may determine that the current traffic volume at each of the remaining points B and C is abnormal.

  In addition, although the case where the number of current traffic exceeding the predetermined number is equal among the current traffic a to e is described here, the determination unit 212 determines whether the current traffic a to current traffic e. If the current traffic volume exceeding the predetermined number is not equal, the current traffic volume from the traffic volume measuring apparatus 10 (not shown) adjacent to each of the traffic volume measuring apparatus 10A and the traffic volume measuring apparatus 10E is further used. A similar determination may be made.

  In the above description, an example in which a branch point or a merge point does not exist on the road has been described. However, the traffic measurement system 1 according to the embodiment of the present invention is also applicable to a case where a branch point or a merge point exists on the road. Can be done. Subsequently, a modified example of the third determination example will be described. FIG. 12 is a diagram for explaining a modification of the third determination example by the determination unit 212. In the third determination example, FIG. 12 shows the traffic volume measuring devices 10A to 10G as the plurality of traffic volume measuring devices 10, but the number of the traffic volume measuring devices 10 is not particularly limited. In addition, FIG. 12 shows an example in which there are branch points and merge points on the road.

  As shown in FIG. 12, the traffic volume measuring devices 10A to 10C and the traffic volume measuring device 10D are adjacent to each other, and the traffic volume measuring device 10D and the traffic volume measuring devices 10E to 10G are adjacent to each other. However, the road merges between the traffic measurement devices 10A to 10C and the traffic measurement device 10D, and the road branches between the traffic measurement device 10D and the traffic measurement devices 10E to 10G. In each of the traffic volume measuring devices 10A to 10G, the current image obtained by imaging the road plane by the imaging unit 170 is acquired.

  Subsequently, in each of the traffic volume measuring devices 10 </ b> A to 10 </ b> G, the current traffic volume is measured by the measurement unit 112, and the current traffic volume is provided to the image analysis device 20 by the output control unit 113. Subsequently, in the image analysis device 20, the current traffic volume provided from each of the traffic volume measuring devices 10A to 10G is acquired by the information acquisition unit 211, and the determination unit 212 determines whether or not the current traffic volume is abnormal. The Here, a case where it is determined whether or not the current traffic volume provided from the traffic volume measuring device 10D is abnormal will be described.

  Specifically, the determination unit 212 is provided from the current traffic volume provided from the traffic volume measuring device 10D and the traffic volume measuring devices 10A to 10C and the traffic volume measuring devices 10E to 10G adjacent to the traffic volume measuring device 10D. Based on the relationship with the current traffic volume, it is determined whether or not the current traffic volume provided from the traffic volume measuring device 10D is abnormal. In the following, the current traffic volume provided from each of the traffic volume measuring devices 10A to 10G may be simply indicated as current traffic volumes a to g.

  In the example shown in FIG. 12, roads merge between the traffic volume measuring devices 10A to 10C and the traffic volume measuring device 10D, and the roads between the traffic volume measuring device 10D and the traffic volume measuring devices 10E to 10G. Is branched. Therefore, the determination unit 212 is a case where the total value from the current traffic volume a to the current traffic volume c is equal to the current traffic volume d, and the total value from the current traffic volume e to the current traffic volume g and the current traffic volume. If the amount d is equal, it may be determined that the current traffic amount d is normal.

  On the other hand, the determination unit 212 is a case where the total value from the current traffic volume a to the current traffic volume c is different from the current traffic volume d, and the current traffic volume g from the current traffic volume d and the current traffic volume e. If the total value from the current traffic volume a to the current traffic volume c and the total value from the current traffic volume e to the current traffic volume g are equal, What is necessary is just to determine whether the quantity d is normal. Specifically, when the total value from the current traffic volume a to the current traffic volume c is equal to the total value from the current traffic volume e to the current traffic volume g, the current traffic volume a to the current traffic volume c It may be determined that the current traffic volume e to the current traffic volume g are all normal and the current traffic volume d is abnormal.

  On the other hand, if the total value from the current traffic volume a to the current traffic volume c is different from the total traffic volume from the current traffic volume e to the current traffic volume g, the current traffic volume a to the current traffic volume g It is difficult to determine which is abnormal.

  Therefore, the determination unit 212 is a case where the total value from the current traffic volume a to the current traffic volume c is different from the current traffic volume d, and the current traffic volume g is calculated from the current traffic volume d and the current traffic volume e. And the total value from the current traffic volume a to the current traffic volume c is different from the total value from the current traffic volume e to the current traffic volume g. Further, the traffic volume measuring device 10 (not shown) adjacent to any one of the traffic volume measuring devices 10A to 10C and the current traffic volume from the traffic volume measuring device 10 (not shown) adjacent to any one of the traffic volume measuring devices 10E to 10G are further used. Thus, the number of equal current traffic volumes as described above may be determined.

  The determination example by the determination unit 212 has been described above. Subsequently, an example in which the display control unit 213 displays the reference image and the abnormality candidate image will be described in more detail.

  FIG. 13 is a diagram illustrating a first screen example whose display is controlled by the display control unit 213. FIG. 14 is a diagram illustrating a second screen example whose display is controlled by the display control unit 213. As illustrated in FIGS. 13 and 14, the display control unit 213 causes the display unit 290 to display the reference image Im1 and the abnormality candidate image Im2 when it is determined that the measurement result is abnormal. As described above, the measurement result does not always remain normal, and a situation in which the measurement result may be abnormal may occur. However, as an example, when the imaging range of the imaging unit 170 is out of the normal range, etc. Measurement results can be abnormal.

However, if the reference image Im1 and the abnormal candidate image Im2 are displayed, it is possible for the inspector to easily check whether the imaging unit 170 is normal. In the example shown in FIG. 13, since the imaging direction of the imaging unit 170 has changed, the inclination of the road plane is different between the reference image Im1 and the abnormal candidate image Im2, and the imaging unit 170 is abnormal. The inspector can easily check.
Other than the reference image Im1 and the abnormal candidate image Im2, the image that is displayed and controlled by the display control unit 213 is not an image, but an image obtained by superimposing each image at a density of 50%. It may be displayed. By displaying in this way, it becomes possible to easily detect parallel movement and rotation of an image that cannot be distinguished by just writing together. Further, such an image and the image shown in FIG. 13 or 14 may be displayed together. Displaying together as shown in FIG. 13 or FIG. 14 allows the inspector to determine whether or not there is an abnormality included in the image while comparing both images.

  Further, when the display control unit 213 determines that the measurement result is abnormal, the display information according to the road plane parameter calculated from the reference image and the road information according to the road plane parameter calculated from the abnormality candidate image At least one of these may be displayed. The road plane parameter may be a traveling direction vector v calculated by the setting unit 111 or a road plane type.

  In the example shown in FIG. 13, the display control unit 213 calculates a two-dimensional vector in the reference image Im1 corresponding to the traveling direction vector calculated from the reference image Im1, and uses the road information M1 indicating the two-dimensional vector as the reference image Im1. And it superimposes on each abnormal candidate image Im2. In the example illustrated in FIG. 14, the display control unit 213 calculates a two-dimensional vector in the abnormal candidate image Im2 corresponding to the traveling direction vector calculated from the abnormal candidate image Im2, and road information M2 indicating the two-dimensional vector. Are superimposed on the reference image Im1 and the abnormal candidate image Im2, respectively. Thus, if the same road information is superimposed on each of the reference image Im1 and the abnormality candidate image Im2, it is possible to make the inspector more easily check the abnormality of the imaging unit 170.

  In the above, when it is determined that the measurement result is abnormal, the display control unit 213 displays the reference image and the abnormal candidate image on the display unit 290 regardless of whether or not the additional condition is satisfied. Explained. However, when it is more certain that the imaging unit 170 is abnormal, the display control unit 213 may display the reference image and the abnormal candidate image on the display unit 290.

  For example, the display control unit 213 may additionally directly compare the reference image and the current image. That is, when it is determined that the measurement result is abnormal, the display control unit 213 determines whether to display the reference image and the abnormal candidate image based on the comparison result between the reference image and the current image. Also good. More specifically, when it is determined that the measurement result is abnormal, the display control unit 213 determines to display the reference image and the abnormal candidate image when the difference between the reference image and the current image exceeds a threshold value. May be.

  For example, the display control unit 213 performs binarization processing on the difference between the reference image and the current image, and if the size of the binarized area exceeds the threshold value, the display control unit 213 displays the reference image and the abnormality candidate image. You may determine with displaying. Alternatively, the display control unit 213 associates feature points between the reference image and the current image, and displays the reference image and the abnormal candidate image when the difference between the associated feature points exceeds a threshold value. It may be determined to be performed.

  For example, the display control unit 213 may additionally compare road plane parameters. That is, when it is determined that the measurement result is abnormal, the display control unit 213 determines the reference image and the reference image based on the comparison result between the road plane parameter calculated from the reference image and the road plane parameter calculated from the current image. It may be determined whether or not to display an abnormal candidate image.

  More specifically, when the display control unit 213 determines that the measurement result is abnormal, the display control unit 213 determines that the difference between the road plane parameter calculated from the reference image and the road plane parameter calculated from the current image exceeds the threshold value. In addition, it may be determined that the reference image and the abnormality candidate image are displayed.

[Description of effects]
As described above, according to the embodiment of the present invention, the image analysis device 20 outputs analysis data obtained by analyzing the image captured by the imaging unit 170, and the road plane is captured by the imaging unit 170. When it is determined that the measurement result measured based on the current image is abnormal, the image analysis unit includes a display control unit 213 that displays a reference image in which a road plane is captured in advance by the imaging unit 170 and an abnormality candidate image. An apparatus 20 is provided.

According to such a configuration, it is possible for the inspector to easily check whether or not the camera used for measuring the traveling state of the vehicle is normal.
According to such a configuration, it is possible to allow an inspector to confirm whether or not the camera used for measurement of the traveling state of the vehicle is normal at a timing when the measurement has an adverse effect, and to easily determine more accurately. .

[Description of modification]
The preferred embodiments of the present invention have been described in detail above with reference to the accompanying drawings, but the present invention is not limited to such examples. It is obvious that a person having ordinary knowledge in the technical field to which the present invention pertains can come up with various changes or modifications within the scope of the technical idea described in the claims. Of course, it is understood that these also belong to the technical scope of the present invention.

  For example, in the above, based on the comparison result between the past measurement result measured based on the reference image and the current measurement result measured based on the current image, whether or not the current measurement result is abnormal is determined. An example of determination is shown. However, in consideration of the possibility that the measurement result changes depending on the time zone, the reference image and the current image to be compared may be images captured in the corresponding time zone. The time zone may be divided every predetermined time such as a day time zone or a night time zone, or may be divided every day such as a weekday or a holiday.

  Each block configuring the control unit 110 includes, for example, a CPU (Central Processing Unit), a RAM (Random Access Memory), and the like, and a program stored in the storage unit 180 is expanded on the RAM and executed by the CPU. Thus, the function can be realized. Or each block which comprises the control part 110 may be comprised by the hardware for exclusive use, and may be comprised by the combination of several hardware.

  Each block constituting the control unit 210 includes, for example, a CPU (Central Processing Unit), a RAM (Random Access Memory), and the like, and a program stored in the storage unit 280 is expanded into the RAM and executed by the CPU. Thus, the function can be realized. Or each block which comprises the control part 210 may be comprised by the hardware for exclusive use, and may be comprised by the combination of several hardware.

  In this specification, the steps described in the flowcharts are executed in parallel or individually even if they are not necessarily processed in time series, as well as processes performed in time series in the described order. Including processing to be performed. Further, it goes without saying that the order can be appropriately changed even in the steps processed in time series.

DESCRIPTION OF SYMBOLS 1 Traffic volume measurement system 10 (10A-10G) Traffic volume measuring apparatus 20 Image analyzer 30 Network 110 Control part 111 Setting part 112 Measurement part 113 Output control part 170 Imaging part 180 Storage part 190 Output part 210 Control part 211 Information acquisition part 212 Determination Unit 213 Display Control Unit 270 Input Unit 280 Storage Unit 290 Display Unit E1 Measurement Range Im1 Reference Image Im2 Abnormality Candidate Image M1, M2 Road Information

Claims (11)

An image analyzer that outputs analysis data obtained by analyzing an image captured by a predetermined imaging unit,
When it is determined that the measurement result measured based on the current image in which the road plane is captured by the predetermined imaging unit is abnormal, the reference image in which the road plane is previously captured by the predetermined imaging unit and the predetermined image A display control unit for displaying the abnormal candidate images of
Image analysis device. The measurement result includes at least one of current traffic volume and current vehicle speed,
The image analysis apparatus according to claim 1. The image analyzer is
A determination unit for determining whether or not the measurement result is abnormal;
The image analysis apparatus according to claim 2. The determination unit determines whether or not the current traffic volume is abnormal based on the relationship between the current traffic volume and the old traffic volume measured in the past.
The image analysis apparatus according to claim 3. The determination unit determines whether or not the current vehicle speed is abnormal based on a relationship between the current vehicle speed and an old vehicle speed measured in the past.
The image analysis apparatus according to claim 3. The determination unit determines that the current traffic volume is abnormal based on a relationship between the current traffic volume and a traffic volume measured based on a captured image captured by another imaging unit adjacent to the predetermined imaging unit. Determine if there is,
The image analysis apparatus according to claim 3. If it is determined that the measurement result is abnormal, the display control unit determines whether to display the reference image and the abnormal candidate image based on a comparison result between the reference image and the current image. judge,
The image analysis apparatus according to claim 1. When it is determined that the measurement result is abnormal, the display control unit, based on a comparison result between a road plane parameter calculated from the reference image and a road plane parameter calculated from the current image, Determining whether to display an image and the abnormal candidate image;
The image analysis apparatus according to claim 1. The display control unit, when it is determined that the measurement result is abnormal, the road information according to the road plane parameter calculated from the reference image and the road according to the road plane parameter calculated from the abnormality candidate image Display at least one of the information,
The image analysis apparatus according to claim 1. The display control unit superimposes and displays the reference image and the abnormality candidate image.
The image analysis apparatus according to claim 1. An image analysis method for outputting analysis data obtained by analyzing an image captured by a predetermined imaging unit,
When it is determined that the measurement result measured based on the current image in which the road plane is captured by the predetermined imaging unit is abnormal, the reference image in which the road plane is previously captured by the predetermined imaging unit and the predetermined image Including a step of displaying an abnormal candidate image of
Image analysis method.

Images