Measuring device and measuring method

Abstract

To provide a measurement device which can measure a measurement object with excellent positional accuracy.SOLUTION: A measurement device 2 comprises: an image acquisition unit 242; a target position specification unit 243 which specifies a position of a target T in a photographed image 5 acquired by the image acquisition unit 242; and an output unit 244 which outputs displacement information indicating a relation between a predetermined reference position of the target and the position specified by the target position specification unit 243. The target T has a pattern in which a first boundary line 51 extending in the first direction is formed by mutually-adjacent two regions, and a second boundary line 52 extending in the second direction intersecting the first direction is formed by mutually-adjacent other two regions. The target position specification unit 243 specifies an intersection point between the first boundary line and the second boundary line in the target in the photographed image as the position of the target in the photographed image.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a measurement apparatus and a measurement method. [Background technology]

[0002] Conventionally, for example, when construction work is carried out near an existing railroad track, the track irregularity is measured during the construction work. Patent Document 1 discloses a method of attaching multiple targets to the rail in advance and measuring the change in the positions of the targets over time with a camera. Patent Document 1 also describes the use of circular patterns as targets and the determination of the center of gravity of the circular patterns. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 3597832 Summary of the Invention [Problem to be solved by the invention]

[0004] The technology in Patent Document 1 is capable of measuring track irregularities with sufficient accuracy for practical purposes, but there is room for improvement, as the position accuracy of the object being measured can decrease when material adheres to the target or when part of the target is obscured by obstacles such as vegetation.

[0005] The present invention has been made in consideration of these points, and has an object to provide a measurement device and a measurement method that are capable of measuring the position of a measurement object with high accuracy. [Means for solving the problem]

[0006] A measuring device of one embodiment of the present invention includes an image acquisition unit that acquires an image generated by an imaging device photographing a target attached to a measurement object, a target position identification unit that identifies a position of the target in the image acquired by the image acquisition unit, and an output unit that outputs displacement information indicating a relationship between a predetermined reference position of the target and the position identified by the target position identification unit, wherein the target has a pattern including a plurality of regions, wherein two adjacent regions form a first boundary line extending in a first direction, and two other adjacent regions form a second boundary line extending in a second direction that intersects with the first direction, and the target position identification unit identifies the intersection of the first boundary line and the second boundary line of the target in the image acquired as the position of the target in the image acquired.

[0007] The target position identification unit may identify a first line connecting two points on the first boundary line, identify a second line connecting other two points on the second boundary line, and identify an intersection of the first line and the second line as the position of the target.

[0008] The output unit may output an alert when the target position identifying unit cannot identify an intersection point between the first boundary line and the second boundary line.

[0009] The captured image may include images of a plurality of the targets, and when the target position identification unit is unable to identify an intersection between the first boundary line and the second boundary line, the output unit may output the captured image together with the alert, the captured image including information indicating a target among the plurality of targets for which the intersection was not identified.

[0010] The output unit may output an alert when at least one of the distance between the two points on the first boundary line and the distance between the other two points on the second boundary line is less than a predetermined threshold set as a threshold for detection accuracy.

[0011] The output unit may output an alert when the distance between the position of a specific target identified by the target position identification unit and the position of another target adjacent to the specific target is equal to or greater than a specific threshold set as a threshold for abnormalities in the target position.

[0012] If the target position identification unit cannot identify an intersection point between the first boundary line and the second boundary line, it may extract a contour shape of the target for which the intersection point was not identified, and identify the center of gravity position of the extracted contour shape as the position of the target.

[0013] The device may further include a target state identification unit that identifies the presence of an object attached to the target or the presence of an obstacle located in front of the target by detecting a contour line in a direction different from the first direction or the second direction, and the output unit may output an alert when it is identified that the object or the obstacle is present.

[0014] The target position identification unit is capable of executing a first operation mode in which the position of the target is identified by identifying the intersection point between the first boundary line and the second boundary line of the target attached to the measurement object, and a second operation mode in which the contour shape of the marker is extracted from an image generated by the imaging device photographing the marker attached to the measurement object, and the center of gravity position of the extracted contour shape is identified as the position of the marker, and may execute either the first operation mode or the second operation mode depending on a selection received from an operator.

[0015] The device may further include a setting reception unit that receives the setting of a detection target area that includes the reference position and is larger than the area of ​​the target, and the target position identification unit may search for the first boundary line and the second boundary line in the detection target area.

[0016] A measurement method according to one embodiment of the present invention includes an image acquisition step of acquiring an image generated by an imaging device photographing a target attached to a measurement object, a target position identification step of identifying a position of the target in the image acquired in the image acquisition step, and an output step of outputting displacement information indicating a relationship between a predetermined reference position of the target and the position identified in the target position identification step, each step being a measurement method executed by a computer, wherein the target has a pattern including a plurality of regions, in which two adjacent regions form a first boundary line extending in a first direction, and two other adjacent regions form a second boundary line extending in a second direction that intersects with the first direction, and in the target position identification step, an intersection of the first boundary line and the second boundary line in the target in the image is identified as the position of the target in the image. Effect of the Invention

[0017] The present invention has an effect of providing a measurement device and a measurement method capable of measuring the position of a measurement object with high accuracy. [Brief description of the drawings]

[0018] [Figure 1] 1 is a diagram showing a configuration of a measurement system according to an embodiment of the present invention; [Diagram 2] FIG. 2 shows a target mounted on a rail. [Diagram 3] FIG. [Figure 4] FIG. 2 is a block diagram showing a configuration of a measurement system. [Diagram 5] 10A and 10B are diagrams for explaining a detection target area set in a captured image. [Figure 6] FIG. 11 is a diagram for explaining a process of identifying a target position. [Figure 7] 11A and 11B are diagrams for explaining a method for identifying the position of a target with a deposit attached thereto. [Figure 8] 10A and 10B are diagrams for explaining a method for identifying a position of a target based on a contour shape of the target. [Figure 9] FIG. 11 is a diagram showing an example of track displacement information; [Figure 10] 11 is a flowchart showing an example of the operation of the measurement system. [Figure 11] 11A and 11B are diagrams illustrating an example in which the reference position of a target cannot be detected with high accuracy. [Figure 12] This is an example of displacement information when the target may be off the rail. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0019] <First embodiment> Hereinafter, an embodiment of the present invention will be described with reference to the drawings. In the following description, the same or corresponding elements are denoted by the same or corresponding reference numerals, and duplicated description will be omitted. Fig. 1 is a diagram showing the configuration of a measurement system S100 according to an embodiment of the present invention. Fig. 2 is a diagram showing a target T attached to a rail R. Fig. 3 is an enlarged view of the target T.

[0020] [Overview of the S100 measurement system] 1, the measurement system S100 of this embodiment mainly includes a camera 1, a measurement device 2, and a target T. The measurement system S100 is a system that measures track irregularities of a track by identifying the positions of multiple targets T attached to a rail R that is an object to be measured. In the following, a track is exemplified as an object to be measured, but the measurement system S100 can also be used to measure other structures such as viaducts and tunnels.

[0021] In this embodiment, a target T attached to a rail R has a cross pattern as shown in Fig. 3, and the measurement device 2 detects an intersection point between a first boundary line 51 and a second boundary line 52 of the cross pattern of the target T, and identifies the intersection point as the position of the target T. The measurement device 2 measures track irregularities of the railroad by continuously detecting the positions of multiple targets T.

[0022] In systems that use targets with circular patterns as in conventional technology, if the target becomes dirty or if part of the target is obscured by obstacles such as vegetation, the exact position of the target T cannot be determined, resulting in a decrease in the accuracy of the measured track irregularities.

[0023] According to the configuration of this embodiment, as long as at least a portion of the first boundary line 51 and the second boundary line 52 is visible, the measurement system S100 can identify the intersection point between the first boundary line 51 and the second boundary line 52. Therefore, even if a portion of the target T is hidden by an attached object or an obstacle, the measurement system S100 can satisfactorily identify the position of the target T, and can accurately measure the track irregularity of the track.

[0024] [Explanation of each part of the measurement system S100] (Camera 1) The camera 1 is an imaging device having an imaging element such as a CCD (Charge Coupled Device) or a CMOS (Complementary Metal Oxide Semiconductor). The camera 1 is supported by, for example, a support 11 and installed at a position higher than the tracks. The camera 1 is controlled in terms of the shooting time, number of shots, shutter speed, etc., by a control signal from, for example, a measurement device 2. The camera 1 simultaneously captures images of multiple targets T attached to a rail R and transmits the generated captured images to the measurement device 2.

[0025] The support pole 11 is installed, for example, at a location outside the area where construction work is to be carried out. As an example, a lighting fixture 12 for illuminating a plurality of targets T is attached to the support pole 11.

[0026] (Target T) As shown in Figs. 2 and 3, the target T is formed in a circular contour shape, for example, and has a cross pattern. Specifically, the target T includes a plurality of regions Ta, Tb, Tc, and Td divided by a first boundary line 51 and a second boundary line 52. In this example, the first boundary line 51 extends in a vertical direction, which is a first direction, and the second boundary line 52 extends in a horizontal direction, which is a second direction. The first boundary line 51 and the second boundary line 52 intersect, for example, at the center of the circle of the target T. The regions Ta and Tc are colored in a first color, and the regions Tb and Td are colored in a second color. The colors of the first color and the second color are arbitrary, but for example, the first color is black and the second color is yellow.

[0027] In this manner, in the target T of this embodiment, a first boundary line 51 is formed by two adjacent regions, and a second boundary line 52 extending therethrough is formed by the other two adjacent regions. The target T is not limited to the pattern as shown in FIG. 3 and may be modified as appropriate. The first boundary line 51 and the second boundary line 52 do not necessarily need to be perpendicular to each other. The contour shape of the target T is not limited to a circle and may be another shape such as a rectangle, a polygon, or an ellipse.

[0028] 2, the target T is formed on the surface of a mounting plate 55. The mounting plate 55 is, for example, a flat member or a member having an L-shaped cross section, and is fixed to the side surface of the rail R at the bottom so that the target T faces the camera 1. The mounting plate 55 may be, for example, a third color different from the first and second colors so that the measurement device 2 can identify the contour shape of the target T.

[0029] As shown in Fig. 1, the targets T are arranged at a predetermined pitch along the rail R at intervals. The "predetermined pitch" is set appropriately depending on the type of measurement object to which the targets T are attached and the details of the construction work, and is, for example, within a range of 1 m to 10 m. The number of targets T attached to the rail R is arbitrary, but in this embodiment, four targets T (targets T1, T2, T3, and T4) are fixed to each rail R.

[0030] As an example, the targets T are arranged on the same side (lower side in the figure) of each rail R. The present invention is not limited to this, and the target T may be arranged on a first side with respect to one rail R, and the target T may be arranged on a second side opposite to the first side with respect to the other rail R.

[0031] The material of the target T may be, for example, a retroreflective material that reflects the light from the lighting fixture 12 incident on the target T in the same direction as the incident direction. When a train runs in a specific direction on the track, it is preferable in one embodiment that the target T is arranged in a direction opposite to the direction in which the train runs (i.e., the target T does not face the train). With such a configuration, dirt and the like is less likely to adhere to the target T, and the measuring device 2 can accurately identify the position of the target T over a long period of time.

[0032] [Measurement device 2] 4 is a block diagram showing the configuration of the measurement system S100. The measurement device 2 is, for example, a computer in which a computer program is installed. The measurement device 2 includes, for example, an input unit 21, a display unit 22, a storage unit 23, and a control unit 24.

[0033] The input unit 21 is a device for receiving input from an operator. The input unit 21 is any device such as a keyboard, a mouse, a touch panel, etc. The display unit 22 is one or more displays that display various information. The input unit 21 and the display unit 22 may be configured as a touch panel display.

[0034] The storage unit 23 is a storage medium that stores various data, and includes a read only memory (ROM), a random access memory (RAM), a hard disk, etc. The storage unit 23 stores computer programs that the control unit 24 executes.

[0035] The storage unit 23 stores the positional relationship between the camera 1 and each target T obtained, for example, by an operator performing surveying. The surveying is performed, for example, using a total station that measures the distance and angle from the camera 1 to each target T. The storage unit 23 also stores various results of calculations performed by each part of the control unit 24, which will be described later.

[0036] (Functional parts of the control unit 24) The control unit 24 has a CPU (Central Processing Unit). For example, the control unit 24 executes a computer program stored in the storage unit 23, thereby functioning as a setting reception unit 241, an image acquisition unit 242, a target position identification unit 243, an output unit 244, and a target state identification unit 245, as shown in FIG.

[0037] The setting reception unit 241 is a functional unit for setting which area of ​​the captured image the measurement device 2 will analyze to identify the position of the target T. FIG. 5 is a diagram for explaining the detection target area A set in the captured image 5. As shown in FIG. 5, the captured image 5 generated by the camera 1 includes an image of the tracks and images of multiple targets T. The measurement device 2 analyzes the captured image 5 to detect the position of each target T, but if the measurement device 2 were to search for the position of each target T over the entire range of the captured image 5, the amount of calculation would increase.

[0038] Therefore, in this embodiment, the setting reception unit 241 receives the setting of the detection target area A (A1 to A4) corresponding to each target T by the operator. Specifically, the setting reception unit 241 receives the setting of the detection target area A by the operator, which includes the reference position (here, the center position) of the target T and is larger than the area of ​​the target T. The detection target area A is a rectangle, for example. The setting reception unit 241 receives the setting of the detection target area A1 corresponding to, for example, each target T1. The same process is performed for the targets T2 to T4, and the detection target areas A2 to A4 are set. In the example of FIG. 5, the detection target area A1 closer to the camera 1 is set to a larger size than the one farther from the camera 1. The detection target area A for each target T that has been set is stored in the storage unit 23.

[0039] The image acquisition unit 242 acquires a captured image 5 generated by the camera 1 capturing an image of a target T attached to a rail R, which is an object to be measured.

[0040] 6 is a diagram for explaining the process of identifying the position of the target T. The target position identifying unit 243 identifies the position of each target T in the captured image 5. Specifically, the target position identifying unit 243 searches for a first boundary line 51 and a second boundary line 52 in a detection target area A (see FIG. 5) set for the captured image 5, and identifies the coordinates of their intersection as the position of the target T.

[0041] More specifically, the target position identifying unit 243 detects two points P1 on the first boundary line 51, and identifies a first straight line L1 connecting these points P1. Similarly, the target position identifying unit 243 detects two points P2 on the second boundary line 52, and identifies a second straight line L2 connecting these two points P2. Then, the target position identifying unit 243 identifies the coordinates of an intersection O1 between the first straight line L1 and the second straight line L2 as the intersection of the first boundary line 51 and the second boundary line 52, and obtains the position of the target T.

[0042] The target position identifying unit 243 searches for the first boundary line 51 and the second boundary line 52 in this manner in each detection target area A, and identifies the position of each target T. The storage unit 23 stores the position of each target T identified by the target position identifying unit 243 in association with the measurement time.

[0043] In addition, the target position identification unit 243 may determine the position of the target T by averaging data of multiple positions of the target T identified based on multiple captured images generated by the camera 1 by taking multiple images at a predetermined time interval.

[0044] Fig. 7 is a diagram for explaining a method for identifying the position of a target T with a deposit 56 attached thereto. Fig. 8 is a diagram for explaining a method for identifying the position of a target based on the contour shape of the target. The target in Fig. 8 is a circular pattern without a cross pattern.

[0045] 7 and 8, a deposit 56 may adhere to the target. An example of the deposit 56 is dirt such as mud or iron powder. Alternatively, snow or the like may adhere to the target as the deposit 56.

[0046] In the case of the target in FIG. 8, in order to identify the target position, the measurement device first obtains the contour shape of the target and identifies the center of gravity of the contour shape. In this method, the measurement device detects multiple feature points p along the target contour and identifies the coordinates of the center of gravity of the shape formed by the multiple feature points p. However, in this method, if an attachment 56 having a shape as shown in FIG. 8 is present, the contour shape of the target T cannot be obtained correctly. Therefore, the identified center of gravity position o1 is shifted from the actual target center o, and as a result, the position accuracy of the measured rail R decreases.

[0047] On the other hand, in the case of the cross pattern target T of this embodiment, as shown in FIG. 7, if four points on the boundary line of the cross pattern can be detected, the intersection point O1 of the first line L1 and the second line L2 can be obtained, and the position of the target T can be identified.

[0048] 9 is a diagram showing an example of displacement information 60 of the rail R. The output unit 244 outputs the displacement information 60 regarding the position of the target T identified by the target position identifying unit 243. As a specific example, the output unit 244 calculates the difference between the coordinates of the initial position of each target T and the coordinates of the position of each target T identified by the target position identifying unit 243, and outputs the relative position calculated by multiplying the difference by a predetermined coefficient according to the positional relationship between the camera 1 and each target T.

[0049] 9 is information indicating the relationship between a reference position (initial position) of the target T determined in advance as an initial setting, and the position of each target T identified by the target position identifying unit 243 based on the captured image 5. In the displacement information 60, the horizontal axis indicates the positions of the targets T1 to T4, and the vertical axis indicates the displacement of each target T. Specifically, the displacement information 60 indicates the relative displacement of each target T with respect to the initial position "0" of each target T.

[0050] In measuring track irregularities, five items are calculated, for example: elevation irregularity (irregularity in the height direction), alignment irregularity (irregularity in the horizontal direction), gauge irregularity (irregularity in the distance between two rails), level irregularity (irregularity in the difference in height between two rails), and planarity irregularity (irregularity in the twisting of the height of two rails). Measurement of each item can be performed by a known method described in, for example, Japanese Patent No. 3597832. The output unit 244 calculates the above five items based on the position of each target T identified by the target position identification unit 243, and outputs the calculation results. Although not shown in the figure, the output unit 244 may output the change over time of each item.

[0051] As described above, in addition to outputting the degree of displacement of the target T with respect to the reference position at a certain time, or outputting the relative positional relationship of multiple targets T, the output unit 244 may output, for example, the absolute position of each target T with respect to the position of a predetermined reference point target. Specifically, the reference point target is, for example, a target placed at a fixed point outside the construction area that is not affected by the construction.

[0052] (Alert output) The output unit 244 outputs various alerts and predetermined information to an operator. The output unit 244 may display the alerts and predetermined information on the display unit 22, or may display them on another device connected to the measuring device 2 via a network (not shown).

[0053] In this embodiment, as described above, the first straight line L1 and the second straight line L2 are identified based on the four points on the target T detected by the target position identifying unit 243, and the intersection of the two straight lines is identified as the position of the target T. However, depending on the range or shape of the attachment 56 attached to the target T, for example, it is expected that the first straight line L1 and / or the second straight line L2 cannot be identified, and the position of the target T cannot be identified.

[0054] Therefore, the output unit 244 outputs an alert, for example, when the target position identification unit 243 cannot identify the first straight line L1 and / or the second straight line L2 and cannot identify the intersection between the first boundary line 51 and the second boundary line 52.

[0055] When the target position identifying unit 243 cannot identify an intersection between the first boundary line 51 and the second boundary line 52, the output unit 244 may output information indicating the target for which the intersection has not been identified among the multiple targets T together with the above-mentioned alert. For example, when an intersection has not been identified for the target T4 among the targets T1 to T4, the output unit 244 outputs information indicating that the target for which the intersection has not been identified is the target T4. Specifically, the output unit 244 may output an image in which text information or image information indicating the unidentified target T is added to the captured image 5. According to such a configuration, a worker who sees the output information can confirm which target T among the multiple targets T has not been identified, and can take measures such as cleaning the target T at the site.

[0056] The output unit 244 may also output an alert when the target position identification unit 243 searches for the first boundary line 51 and the second boundary line 52 in the detection target area A but is unable to find the first boundary line 51 or the second boundary line 52.

[0057] The target state identifying unit 245 identifies, for example, that an object 56 is attached to the target T based on the captured image 5. As an example, the target state identifying unit 245 identifies the presence of the object 56 attached to the target T by detecting a contour line in a direction different from the first direction in which the first straight line L1 of the target T extends or the second direction in which the second straight line L2 extends in each detection target area A. Specifically, the target state identifying unit 245 determines that the object 56 is present when the detected contour line has a length equal to or greater than a predetermined threshold value.

[0058] In addition to the attachment directly attached to the target T, for example, a situation is assumed in which the cross pattern of the target T cannot be photographed correctly due to the presence of a part of a plant or the like in front of the target T. In this regard, the target state identification unit 245 may identify the presence of an obstacle located in front of the target T. As described above, the target state identification unit 245 may identify the presence of an obstacle by detecting a contour line in a direction different from the first direction in which the first straight line L1 of the target T extends or the second direction in which the second straight line L2 extends. As an example, the target state identification unit 245 may use a trained model that has been trained to classify attachments and obstacles, and identify attachments and obstacles by image recognition. The target state identification unit 245 may have a function of identifying the type of attachment or the type of obstacle. The output unit 244 outputs, for example, the identification result of the target state identification unit 245 to the operator.

[0059] [Measurement of trajectory irregularities] The operation of the measurement system S100 configured as described above will be described below. Fig. 10 is a flow chart showing an example of the operation of the measurement system S100.

[0060] Step S1 is an initial setting step. First, in step S1, the measurement device 2 identifies the positions of multiple targets T attached to the rail R, and stores the identified positions in the memory unit 23 as reference positions of the targets T. In step S1, distance relationship information obtained by an operator by actually measuring the positional relationship between the camera 1 and each target T through surveying is also stored in the memory unit 23. In addition, the setting reception unit 241 receives the setting of the detection target area A (see FIG. 6) for each target T by the operator, and the setting information received by the setting reception unit 241 is stored in the memory unit 23. After such initial setting is completed, operation of measuring track irregularities by the measurement system S100 is started.

[0061] In step S2, the measurement device 2 operates the camera 1 at a predetermined measurement time set in advance to capture images of multiple targets T. As an example, the camera 1 captures images of the target T a predetermined number of times within a set predetermined period of time to generate multiple captured images 5.

[0062] Next, in step S3, based on the captured image 5 acquired by the image acquisition unit 242 from the camera 1, the target position identification unit 243 analyzes the image in each detection target area A in the captured image 5. Specifically, the target position identification unit 243 detects two points P1, P1 on the cross pattern of the target T to identify a first straight line L1, and detects other two points P2, P2 to identify a second straight line L2, and identifies the intersection O1 between them as the position of the target T. The target position identification unit 243 performs such processing for all targets T, and the identified positions of the targets T are stored in the storage unit 23.

[0063] Next, in step S4, the output unit 244 calculates, for example, five items of track-related irregularities, including elevation irregularities, alignment irregularities, gauge irregularities, level irregularities, and planarity irregularities, based on the position of the target T identified by the target position identification unit 243 and the positional relationship between the camera 1 and the target T pre-stored in the storage unit 23. Then, in step S5, the output unit 244 outputs the calculation results.

[0064] Next, in step S6, if the value of any of the above items is equal to or greater than a predetermined threshold and the calculation result is not within a predetermined range (No in step S6), the output unit 244 outputs an alert. In step S6, if the calculation result of the above items is within the predetermined range, no alert is output, and steps S2 to S5 are repeated. Note that the timing and number of times that an alert is issued, and the contents of the alert can be changed in various ways, and for example, an alert may be issued multiple times depending on the degree of trajectory deviation.

[0065] By operating in this manner, the measuring device 2 automatically measures the track irregularities of the track, which is the object to be measured, while the measurement system S100 is in operation, and an operator can monitor the condition of the track by checking the output results of the measuring device 2.

[0066] (Effects of the Configuration of the First Embodiment) In the configuration of this embodiment as described above, the measurement device 2 of the measurement system S100 detects points P1 and P2 on the target T and determines the intersection O1 of the first line L1 and the second line L2 to identify the position of the target T. Therefore, even if part of the target T is hidden by an attached object or an obstacle, as long as points P1 and P2 on the target T can be detected, the position of the target T can be identified and the track irregularity of the track can be measured with high accuracy.

[0067] In addition, in principle, the target T of this embodiment does not need to detect the contour shape of the target T. In the case of a conventional circular pattern, the size of the circular pattern is somewhat smaller than the height dimension of the mounting plate 55 so that the contour shape of the target can be easily detected. With this configuration, and by making the target and the mounting plate 55 different in color, it becomes easier for the measurement device to detect the contour shape of the target, which is a circular pattern. In this configuration, the size of the circular pattern needs to be relatively small, but in the target T of the cross pattern of this embodiment, for example, the diameter of the target T may be approximately the same as the height dimension of the mounting plate 55, and therefore the size of the target T can be large. As a result, the size of the target T in the captured image becomes large, resulting in an effect of improving the identifiability of the target T.

[0068] Furthermore, when the target position identification unit 243 cannot identify the intersection between the first boundary line 51 and the second boundary line 52, the output unit 244 outputs an alert, so that the worker can know the detection abnormality of the position of the target T. In particular, when such a detection abnormality occurs, the output unit 244 outputs a captured image including information indicating the target among the multiple targets for which the intersection has not been identified, together with the alert, so that the worker can confirm the contents and confirm which target is abnormal.

[0069] <Variation 1> In the above embodiment, the intersection of the first boundary line 51 and the second boundary line 52 is detected based on the image of the target T, but when the target position identifying unit 243 cannot identify the intersection of the first boundary line 51 and the second boundary line 52, the target position identifying unit 243 may extract the contour shape of the target T for which the intersection was not identified, and identify the center of gravity of the extracted contour shape as the position of the target T. Specifically, the target position identifying unit 243 identifies a plurality of feature points along the contour of the target T, and identifies the center of gravity of the shape formed by the plurality of feature points as the position of the target T.

[0070] According to this configuration, even if the intersection point between the first boundary line 51 and the second boundary line 52 cannot be identified due to obstacles such as attached matter 56 or plants, the position of the target T can be identified if the contour shape of the target T can be characterized. Therefore, compared to a configuration in which the position of the target T is identified only by a method of identifying the intersection point between the first boundary line 51 and the second boundary line 52, it is possible to reduce the frequency of occurrences in which the position of the target T cannot be identified.

[0071] <Variation 2> Fig. 11 is a diagram showing an example in which the position of the target T cannot be detected with high accuracy. As described with reference to Fig. 6, the target position identification unit 243 detects points P1 and P2 on the first boundary line 51 and the second boundary line 52 of the target T to identify the first straight line L1 and the second straight line L2. Therefore, depending on the shape of the attached object or obstacle, as shown in Fig. 11, the distance d1 between the points P1 and the distance d2 between the points P2 may be short. In this case, the directions of the first straight line L1 and the second straight line L2 may be significantly deviated from the first boundary line 51 and the second boundary line 52, and the intersection O1 between the first straight line L1 and the second straight line L2 may not be identified with high accuracy.

[0072] Therefore, in one modified example of the present invention, the output unit 244 may output an alert when at least one of the distance d1 between two points P1 on the first boundary line 51 and the distance d2 between other two points P2 on the second boundary line 52 is less than a predetermined threshold. The "less than the predetermined threshold" is a threshold set as a threshold related to detection accuracy, and may be a value set by an operator or a value set by the measurement device 2. When the distance d1 or the distance d2 is less than the predetermined threshold, the target position identification unit 243 may not identify the intersection point between the first line L1 and the second line L2, but may re-detect the points P1, P1, P2, and P2 based on the captured image 5 in which the camera 1 captures the target T again, and may identify the intersection point between the first line L1 and the second line L2 when the distance d1 and the distance d2 are equal to or greater than the predetermined threshold.

[0073] The memory unit 23 stores multiple sizes of the target T in association with multiple of the above thresholds, and the output unit 244 or the target position identification unit 243 may refer to the memory unit 23 and automatically determine the associated threshold based on the size of the target T identified by the target position identification unit 243, and perform the above processing.

[0074] <Variation 3> FIG. 12 is an example of displacement information when there is a possibility that the target T has come off the rail R. When the measurement target is something like a rail R, even if the shape of the rail R is deformed for some reason, it is assumed that the rail R will deform gently overall, and it is unlikely that only one part of the rail R will be locally displaced significantly compared to the rest. In FIG. 12, as an example, the position of the target T3 is displaced significantly compared to the positions of the other targets T1, T2, and T4. In such a case, it is assumed that the target T3 may have come off the rail R.

[0075] Therefore, the output unit 244 may output an alert when the distance d3 between the position of a specific target identified by the target position identification unit 243 (e.g., the position of target T3) and the position of another target adjacent to it (e.g., target T4) is equal to or greater than a specific threshold set as a threshold for abnormalities in the target position.

[0076] <Modification 4> In the above embodiment, the position of the target T is specified by obtaining the intersection of the first boundary line 51 and the second boundary line 52 on the target T. However, in the measurement system S100, it is also preferable to be able to select between a method of determining the position of the target by obtaining the position of the center of gravity from the outline shape of the specified target, and a method of using a cross pattern.

[0077] Therefore, the target position identifying unit 243 can execute a first operation mode in which the position of the target T is identified by identifying the intersection between the first boundary line 51 and the second boundary line 52 in the target T attached to the rail R, which is the measurement object, and a second operation mode in which the contour shape of the sign is extracted in the captured image 5 generated by the camera 1 photographing a plurality of signs attached to the rail R, and the position of the center of gravity of the extracted contour shape is identified as the position of the sign, and either the first operation mode or the second operation mode may be executed according to the selection received from the operator. The "sign" is, for example, a circular pattern, and the circular pattern may be attached to the rail R separately from the target T having a cross pattern.

[0078] The target position identification unit 243 may, for example, refer to the memory unit 23 in which the type of construction object and the type of operation mode are associated with each other, and automatically determine the operation mode according to the type of construction object for which the work has been input.

[0079] Although the present invention has been described above using the embodiments, the technical scope of the present invention is not limited to the scope described in the above embodiments, and various modifications and changes are possible within the scope of the gist of the present invention. For example, all or part of the device can be configured by distributing or integrating functionally or physically in any unit. In addition, new embodiments resulting from any combination of multiple embodiments are also included in the embodiments of the present invention. The effect of the new embodiment resulting from the combination combines the effect of the original embodiment. [Explanation of symbols]

[0080] 1 Camera 2. Measurement equipment 5. Captured images 11 Posts 12 Lighting equipment 21 Input section 22 Display section 23 Memory section 24 Control Unit 51 First Boundary 52 Second Boundary 55 Mounting plate 56 Adhesion 60 Displacement Information 241 Settings Reception Department 242 Image Acquisition Unit 243 Target Location Identification Unit 244 Output section 245 Target State Identification Unit A Detection area L1 1st straight line L2 2nd straight line o Target Centered o1 Center of gravity position p feature points R rail S100 Measurement System T Target

Claims

1. an image acquisition unit that acquires a captured image generated by an imaging device capturing an image of a target attached to a measurement object; a target position identifying unit that identifies a position of the target in the captured image acquired by the image acquiring unit; an output unit that outputs displacement information indicating a relationship between a predetermined reference position of the target and the position identified by the target position identifying unit; Equipped with The target has a pattern including a plurality of regions, in which a first boundary line extending in a first direction is formed by two adjacent regions, and a second boundary line extending in a second direction intersecting the first direction is formed by other two adjacent regions, the target position identification unit identifies an intersection point between the first boundary line and the second boundary line of the target in the captured image as the position of the target in the captured image, and when the intersection point between the first boundary line and the second boundary line cannot be identified, extracts a contour shape of the target for which the intersection point has not been identified, and identifies a center of gravity position of the extracted contour shape as the position of the target. Measuring equipment.

2. The target position identification unit is Identifying a first line connecting two points on the first boundary line; identifying a second line connecting two other points on the second boundary line; Identifying an intersection point between the first line and the second line as the position of the target; The measurement device according to claim 1 .

3. The output unit outputs an alert when the target position identifying unit cannot identify an intersection point between the first boundary line and the second boundary line. The measuring device according to claim 1 or 2.

4. The captured image includes images of a plurality of the targets, When the target position identifying unit cannot identify an intersection between the first boundary line and the second boundary line, the output unit outputs, together with the alert, the captured image including information indicating a target among the plurality of targets for which the intersection has not been identified. The measurement device according to claim 3.

5. the output unit outputs an alert when at least one of a distance between the two points on the first boundary line and a distance between the other two points on the second boundary line is less than a predetermined threshold set as a threshold related to detection accuracy. The measurement device according to claim 2 .

6. The output unit outputs an alert when a distance between a position of the predetermined target identified by the target position identifying unit and a position of another target adjacent to the predetermined target is equal to or greater than a predetermined threshold set as a threshold for an abnormality in the target position. The measuring device according to claim 1 or 2.

7. a target state identification unit that identifies the presence of an object attached to the target or the presence of an obstacle located in front of the target by detecting a contour line in a direction different from the first direction or the second direction, The output unit outputs an alert when the presence of the attachment or the obstacle is identified. The measuring device according to claim 1 or 2.

8. The target position identification unit is a first operation mode for identifying a position of the target by identifying an intersection point between the first boundary line and the second boundary line on the target attached to the measurement object; a second operation mode in which a contour shape of the marker is extracted from a captured image generated by the imaging device capturing an image of the marker attached to the measurement object, and the position of the center of gravity of the extracted contour shape is identified as the position of the marker; execute either the first operation mode or the second operation mode in response to a selection received from an operator; The measuring device according to claim 1 or 2.

9. The apparatus further includes a setting receiving unit that receives a setting of a detection target area that includes the reference position and is larger than an area of ​​the target, the target position identifying unit searches for the first boundary line and the second boundary line in the detection target area; The measuring device according to claim 1 or 2.

10. an image acquiring step of acquiring an image generated by an imaging device capturing an image of a target attached to a measurement object; a target position specifying step of specifying a position of the target in the captured image acquired in the image acquiring step; an output step of outputting displacement information indicating a relationship between a predetermined reference position of the target and the position identified in the target position identification step; Each step of the method is implemented by a computer. The target has a pattern including a plurality of regions, in which a first boundary line extending in a first direction is formed by two adjacent regions, and a second boundary line extending in a second direction intersecting the first direction is formed by other two adjacent regions, In the target position specifying step, an intersection point between the first boundary line and the second boundary line of the target in the captured image is specified as a position of the target in the captured image; The method further includes a step of, when an intersection point between the first boundary line and the second boundary line cannot be specified, extracting a contour shape of the target for which the intersection point has not been specified, and specifying a center of gravity position of the extracted contour shape as a position of the target. Measurement method.

Images