Detection device, detection method, and detection program

Abstract

To detect a linear object in an image more accurately.SOLUTION: A detection device that detects a linear object appearing in an image, includes: an acquisition unit configured to acquire a binarized image in which an object area that satisfies a predetermined condition and an area other than the object area are separated in the image; a centerline detection unit configured to detect a centerline of the object area in the binarized image acquired by the acquisition unit; a contour line detection unit configured to detect a contour line of the object area in the binarized image; and a determination unit configured to perform processing of determining that the object area is the linear object based on the centerline detected by the centerline detection unit and the contour line detected by the contour line detection unit.SELECTED DRAWING: Figure 3

Description

Technical Field

[0001] The present disclosure relates to a detection device, a detection method, and a detection program.

Background Art

[0002] Conventionally, a technique for detecting a linear object shown in an image by analyzing the image is known. For example, Patent Document 1 (Japanese Unexamined Patent Application Publication No. 2013-131174) discloses a strip structure detection device as follows. That is, the strip structure detection device is a device that detects a strip structure having a predetermined width from an input image. At a plurality of search positions in the input image, a plurality of first discrimination positions on the circumference of an inner circle having a diameter equal to or less than the predetermined width or inside the inner circle centered on the search position, and a plurality of second discrimination positions on the circumference of an outer circle having a diameter greater than the predetermined width centered on the search position or in a region between the circumferences of the outer circle and the inner circle are discriminated as to whether the image features are the same as or similar to the image features of the strip structure. When it is discriminated that the image features at the first discrimination positions are the same as or similar to the image features of the strip structure, and a continuous region composed of positions among the second discrimination positions that are neither the same nor similar to the image features of the strip structure exists so as to face each other across the inner circle, a strip structure candidate detection means for detecting the search position as a strip structure candidate point, and a strip structure detection means for detecting the strip structure by fitting a line to the strip structure candidate point group are provided.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, due to noise and background effects in the image, it may not be possible to accurately detect the linear object being targeted.

[0005] This disclosure was made to solve the above-mentioned problems, and its purpose is to provide a detection device, a detection method, and a detection program that can more accurately detect linear objects appearing in an image. [Means for solving the problem]

[0006] The detection device disclosed herein is a detection device for detecting linear objects in an image, comprising: an acquisition unit that acquires a binarized image in which a target region satisfying predetermined conditions is separated from a region other than the target region in the image; a center line detection unit that detects the center line of the target region in the binarized image acquired by the acquisition unit; a contour line detection unit that detects the contour line of the target region in the binarized image; and a determination unit that performs a determination process to determine whether the target region is the linear object based on the center line detected by the center line detection unit and the contour line detected by the contour line detection unit.

[0007] One aspect of this disclosure can be implemented not only as a detection device having such characteristic processing unit, but also as a semiconductor integrated circuit that implements part or all of the detection device, or as a monitoring system including the detection device. [Effects of the Invention]

[0008] According to this disclosure, linear objects in an image can be detected more accurately. [Brief explanation of the drawing]

[0009] [Figure 1] Figure 1 is a diagram showing the configuration of the monitoring system according to the embodiment of this disclosure. [Figure 2] Figure 2 shows a cable that is monitored by the monitoring system according to the embodiment of the present disclosure. [Figure 3]Figure 3 shows the configuration of the detection device according to the embodiment of this disclosure. [Figure 4] Figure 4 shows an example of an extracted image generated by the generation unit in the detection device according to the embodiment of this disclosure. [Figure 5] Figure 5 shows an example of a binarized image generated by the generation unit in the detection device according to the embodiment of this disclosure. [Figure 6] Figure 6 shows an example of a centerline detected by the centerline detection unit in the detection device according to the embodiment of this disclosure. [Figure 7] Figure 7 shows an example of a contour line detected by the contour line detection unit in the detection device according to the embodiment of this disclosure. [Figure 8] Figure 8 shows an example of a determination process by the detection unit in the detection device according to the embodiment of this disclosure. [Figure 9] Figure 9 shows another example of the determination process by the detection unit in the detection device according to the embodiment of this disclosure. [Figure 10] Figure 10 shows another example of the determination process by the detection unit in the detection device according to the embodiment of the present disclosure. [Figure 11] Figure 11 shows an example of branch removal processing by the detection unit in the detection device according to the embodiment of this disclosure. [Figure 12] Figure 12 shows an example of a target area in which a branch has been removed by the detection unit in the detection device according to the embodiment of this disclosure. [Figure 13] Figure 13 is a flowchart illustrating an example of the operation procedure when the detection device according to the embodiment of this disclosure detects a cable appearing in an captured image. [Modes for carrying out the invention]

[0010] First, the embodiments of this disclosure will be listed and explained.

[0011] (1) The detection device according to an embodiment of the present disclosure is a detection device that detects a linear object reflected in an image, and includes an acquisition unit that acquires a binarized image in which a target region satisfying a predetermined condition and a region other than the target region are separated in the image, a center line detection unit that detects a center line of the target region in the binarized image acquired by the acquisition unit, a contour line detection unit that detects a contour line of the target region in the binarized image, and a determination unit that performs a determination process as to whether the target region is the linear object based on the center line detected by the center line detection unit and the contour line detected by the contour line detection unit.

[0012] In this way, by acquiring a binarized image in which a target region and a region other than the target region are separated in an image and performing a determination process based on the center line and the contour line of the target region, the shape of the object in the image can be grasped more accurately from the center line and the contour line, and for example, a linear target region can be determined to be a linear object. Therefore, the linear object reflected in the image can be detected more accurately.

[0013] (2) In the above (1), the determination unit may perform the determination process based on the distance between the center line and the contour line.

[0014] With such a configuration, based on the distance between the center line and the contour line, a linear target region with a uniform width can be determined to be a linear object.

[0015] (3) In the above (2), the determination unit may perform the determination process based on the variation of the distance.

[0016] With such a configuration, while reducing the influence of noise, background, etc. reflected in the image, a linear target region with a uniform width can be determined to be a linear object.

[0017] (4) In the above (3), the determination unit may determine that the target region is the linear object when the variation is less than or equal to a predetermined value.

[0018] In linear target regions, the variation in the distance between the center line and the contour line is small. With this configuration, it is possible to determine that such a target region with small variation is a linear object through a simple process.

[0019] (5) In any of (1) to (4) above, the determination unit may further determine whether the target area is the linear object to be detected based on the length of the target area.

[0020] With this configuration, for example, it is possible to selectively detect linear objects that satisfy predetermined length conditions from among multiple linear objects that appear in an image.

[0021] (6) In (5) above, the determination unit may determine that the target region whose length is less than a predetermined value is not the linear object to be detected.

[0022] With this configuration, for example, it is possible to selectively detect linear objects of a predetermined length or longer from among multiple linear objects that appear in an image.

[0023] (7) In any of (1) to (6) above, the detection device may further include a removal unit that generates an image including the target region from which the branching portion has been removed if the target region determined by the determination unit to be a linear object has a branching portion.

[0024] This configuration allows for a more accurate determination of the state of a linear object based on the target area from which the branching points have been removed.

[0025] (8) The acquisition unit may generate the binarized image based on the detection result of the position of the linear object by a sensor outside the detection device.

[0026] With this configuration, a binarized image in which the linear object is displayed as the target region can be generated more reliably based on the detection result of the linear object's position, thus enabling more reliable detection of the linear object in the judgment process.

[0027] (9) A detection method according to an embodiment of the present disclosure is a detection method in a detection device for detecting linear objects in an image, comprising the steps of: acquiring a binarized image in which a target region satisfying predetermined conditions and a region other than the target region are separated in the image; detecting the center line of the target region in the acquired binarized image; detecting the contour line of the target region in the binarized image; and performing a determination process to determine that the target region is the linear object based on the detected center line and contour line.

[0028] In this way, by obtaining a binarized image in which the target region and the surrounding region are separated, and performing a determination process based on the center line and contour line of the target region, the shape of an object in the image can be more accurately determined from the center line and contour line, and for example, a linear target region can be determined to be a linear object. Therefore, linear objects appearing in the image can be detected more accurately.

[0029] (10) The detection program according to the embodiment of the present disclosure is a detection program used in a detection device for detecting linear objects in an image, and is a program for causing a computer to function as: an acquisition unit that acquires a binarized image in which a target region satisfying predetermined conditions in the image is divided into a target region and a region other than the target region; a center line detection unit that detects the center line of the target region in the binarized image acquired by the acquisition unit; a contour line detection unit that detects the contour line of the target region in the binarized image; and a determination unit that performs a determination process to determine whether the target region is the linear object based on the center line detected by the center line detection unit and the contour line detected by the contour line detection unit.

[0030] In this configuration, a binarized image is obtained in which the target region and the region outside the target region are separated, and a determination process is performed based on the center line and contour line of the target region. This allows for a more accurate understanding of the shape of an object in the image from the center line and contour line, and enables the determination of, for example, a linear target region as a linear object. Therefore, linear objects appearing in the image can be detected more accurately.

[0031] Embodiments of this disclosure will be described below with reference to the drawings. In the drawings, the same or corresponding parts are denoted by the same reference numerals, and their descriptions will not be repeated. Furthermore, at least some of the embodiments described below may be combined in any way.

[0032] [Configuration and Basic Operation] <Detection System> Figure 1 is a diagram showing the configuration of a monitoring system according to an embodiment of the present disclosure. Referring to Figure 1, the monitoring system 201 comprises an imaging device 111, a detection device 101, and an alarm device 121. For example, the monitoring system 201 is used in a factory that produces products. The imaging device 111 is a two-dimensional imaging device such as a camera, LiDAR (Laser Imaging Detection and Ranging), and millimeter-wave radar.

[0033] Figure 2 shows a cable that is monitored by the monitoring system according to an embodiment of the present disclosure. Referring to Figure 2, the dispensing device 131 dispenses the cable 10 used in the production of products in the factory. The conveying device 141 conveys the cable 10 dispensed from the dispensing device 131 to a subsequent device.

[0034] For example, if the conveying speed of the cable 10 by the conveying device 141 is slower than the unwinding speed of the cable 10 by the unwinding device 131, the cable 10 may sag between the unwinding device 131 and the conveying device 141, potentially damaging the cable 10. The monitoring system 201 monitors the condition of the cable 10 between the unwinding device 131 and the conveying device 141. The cable 10 is an example of a linear object.

[0035] The imaging device 111 periodically or irregularly captures an image of the imaging area between the feed-out device 131 and the transport device 141, thereby generating an image showing the cable 10, and transmits imaging information indicating the generated image to the detection device 101.

[0036] The detection device 101 receives imaging information from the imaging device 111 and detects the cable 10 that appears in the image captured by the received imaging information. The detection device 101 may detect a straight cable 10 or a curved cable 10. Based on the detection result of the cable 10, the detection device 101 generates cable status information indicating the state of the detected cable 10 and transmits the generated cable status information to the alarm device 121. For example, the detection device 101 transmits cable status information indicating the deflection amount, curvature, and angle of the cable 10 to the alarm device 121.

[0037] The alarm device 121 receives cable status information from the detection device 101, and if it determines that the cable 10 is in an abnormal state based on the received cable status information, it processes a notification of the determination result to the user of the monitoring system 201.

[0038] <Detection device> Figure 3 is a diagram showing the configuration of a detection device according to an embodiment of the present disclosure. Referring to Figure 3, the detection device 101 comprises a generation unit 11, a centerline detection unit 21, a contour line detection unit 31, a detection unit 41, and a storage unit 51. The generation unit 11 is an example of an acquisition unit. The detection unit 41 is an example of a determination unit and an example of a removal unit. Some or all of the generation unit 11, the centerline detection unit 21, the contour line detection unit 31, and the detection unit 41 are implemented, for example, by a processing circuit (Circuitry) including one or more processors. The storage unit 51 is, for example, a non-volatile memory included in the processing circuit.

[0039] (Generation part) Figure 4 shows an example of an extracted image generated by the generation unit in the detection device according to the embodiment of the present disclosure. Referring to Figure 4, the generation unit 11 receives imaging information from the imaging device 111 and generates an extracted image P1 by extracting a predetermined portion in which the cable 10 is visible from the imaging image indicated by the received imaging information.

[0040] Figure 5 shows an example of a binarized image generated by the generation unit in the detection device according to the embodiment of the present disclosure. Referring to Figure 5, the generation unit 11 generates a binarized image P2 in which the extracted image P1 is divided into target regions R1, R2, R3, R4 that satisfy predetermined conditions and regions other than the target regions R1, R2, R3, R4. Hereinafter, each of the target regions R1, R2, R3, R4 will also be referred to as target region R.

[0041] For example, the target region R is a region that satisfies the above predetermined condition that the pixel density value in the extracted image P1 is less than or equal to the threshold ThA.

[0042] More specifically, the generation unit 11 compares the density value of each pixel in the extracted image P1 with a threshold ThA, and generates a binarized image P2 by converting the density value of each pixel in the extracted image P1 based on the comparison result. As an example, the generation unit 11 generates a two-tone binarized image P2 in which pixels in the target region R whose density value is less than or equal to the threshold ThA are converted to white, and pixels whose density value is greater than the threshold ThA are converted to black. The threshold ThA may be a predetermined value, or it may be set according to the density value of each pixel in the extracted image P1. The generation unit 11 stores image information showing the generated binarized image P2 in the storage unit 51. The generation unit 11 may also be configured to generate a binarized image P2 in which each pixel in the extracted image P1 is converted to white or black according to its color.

[0043] (Centerline detection unit) Figure 6 shows an example of a center line detected by the center line detection unit in the detection device according to the embodiment of the present disclosure. Referring to Figure 6, the center line detection unit 21 detects the center line of the target region R in the binarized image P2 generated by the generation unit 11.

[0044] More specifically, when the image information is stored in the storage unit 51 by the generation unit 11, the centerline detection unit 21 detects the centerline of the target region R by performing a thinning process that thins the target region R in the binarized image P2 indicated by the image information. Specifically, in the thinning process, the centerline detection unit 21 detects the centerline of the target region R by thinning the target region R from the outside according to algorithms such as "Hilditch," "Tamura's method," and "Zhang Suen." The centerline detection unit 21 detects the centerline for each target region R and generates centerline information indicating the position of each centerline in the binarized image P2, which is then output to the detection unit 41.

[0045] (Contour detection unit) Figure 7 shows an example of a contour line detected by the contour line detection unit in the detection device according to the embodiment of the present disclosure. Referring to Figure 7, the contour line detection unit 31 detects the contour line of the target region R in the binarized image P2 generated by the generation unit 11.

[0046] More specifically, when the image information is stored in the storage unit 51 by the generation unit 11, the contour detection unit 31 detects contour lines that indicate the contour of the target region R in the binarized image P2 shown by the image information. The contour detection unit 31 detects contour lines for each target region R, generates contour line information indicating the position of each contour line in the binarized image P2, and outputs it to the detection unit 41.

[0047] (Detection unit) The detection unit 41 performs a determination process to determine whether the target region R is the cable 10, based on the center line detected by the center line detection unit 21 and the contour line detected by the contour line detection unit 31. More specifically, the detection unit 41 receives center line information and contour line information from the center line detection unit 21 and the contour line detection unit 31, and acquires image information from the storage unit 51. Based on the received center line information and contour line information, the detection unit 41 performs a determination process to determine whether the target region R in the binarized image P2 shown by the acquired image information is the cable 10.

[0048] For example, the detection unit 41 performs a determination process for the target region R based on the distance d between the center line of the target region R and the contour line of the target region R.

[0049] (Example of judgment process 1) Figure 8 shows an example of a determination process by the detection unit in a detection device according to an embodiment of the present disclosure. Figure 8 shows the determination process for the target region R2 by the detection unit 41. Referring to Figure 8, the detection unit 41 calculates the distance d between multiple positions on the contour line of the target region R2 and the center line. The detection unit 41 performs a determination process based on the variation of the calculated distance d.

[0050] Here, the distance d in target regions R2 and R4, where the width is not uniform, shows greater variability compared to the distance d in target regions R1 and R3, where the width is uniform.

[0051] The detection unit 41 determines whether the target area R is a cable 10 based on the result of comparing the variation of distance d in the target area R with a predetermined threshold Th1. More specifically, the detection unit 41 calculates the variance V of distance d in the target area R2 and compares the calculated variance V with the threshold Th1. If the detection unit 41 determines that the target area R2 is not a cable 10, the variance V of distance d in the target area R2 is greater than the threshold Th1.

[0052] (Example of judgment process 2) Figure 9 shows another example of the determination process by the detection unit in the detection device according to the embodiment of the present disclosure. Figure 9 shows the determination process for the target region R3 by the detection unit 41. Referring to Figure 9, the detection unit 41 calculates the distance d between multiple positions on the contour line of the target region R3 and the center line, and performs a determination process based on the variation of the calculated distance d.

[0053] The detection unit 41 determines that the target area R is a cable 10 if the variation in distance d in the target area R is less than or equal to the threshold Th1. More specifically, the detection unit 41 calculates the variance V of distance d in the target area R3 and compares the calculated variance V with the threshold Th1. The detection unit 41 determines that the target area R3 is a cable 10 if the variance V of distance d in the target area R3 is less than or equal to the threshold Th1.

[0054] For example, the detection unit 41 further determines whether the target area R is the cable 10 to be detected based on the length of the target area R. More specifically, the detection unit 41 determines that a target area R whose length is less than a predetermined value is not the cable 10 to be detected. Specifically, if the detection unit 41 determines that the target area R3 is the cable 10, it compares the length of the target area R3 with a predetermined threshold Th2, and if the length of the target area R3 is less than the threshold Th2, it determines that the target area R3 is not the cable 10 to be detected.

[0055] (Example of judgment process 3) Figure 10 shows another example of the determination process by the detection unit in the detection device according to the embodiment of the present disclosure. Figure 10 shows the determination process for the target region R1 by the detection unit 41. Referring to Figure 10, the detection unit 41 calculates the distance d between multiple positions on the contour line of the target region R1 and the center line, and performs a determination process based on the variation of the calculated distance d.

[0056] The detection unit 41 calculates the variance V of distance d in the target region R1 and compares the calculated variance V with the threshold Th1. If the variance V of distance d in the target region R1 is less than or equal to the threshold Th1, the detection unit 41 determines that the target region R1 is the cable 10. Then, the detection unit 41 compares the length of the target region R1 with the threshold Th2, and if the length of the target region R1 is greater than or equal to the threshold Th2, the detection unit 41 determines that the target region R1 is the cable 10 to be detected.

[0057] Figure 11 shows an example of branch removal processing by the detection unit in the detection device according to the embodiment of the present disclosure. Referring to Figure 11, if the target area R1 which is determined to be a cable 10 has a branch, the detection unit 41 performs branch removal processing to remove the branch.

[0058] More specifically, if the center line of the target region R1 has a branching point, the detection unit 41 divides the center line into three dividing lines connecting the branching point and the endpoint, and divides the target region R1 into segments S1, S2, and S3, each containing a dividing line. The detection unit 41 then removes segment S3, which contains the shortest dividing line among segments S1, S2, and S3, from the target region R1. If the target region R1 has four or more segments, the detection unit 41 repeats the removal of the segment containing the shortest dividing line until there are no more branching points.

[0059] Figure 12 shows an example of a target region from which a branch has been removed by the detection unit in the detection device according to an embodiment of the present disclosure. Referring to Figure 12, the detection unit 41 generates an image including the target region R1s from which segment S3 has been removed.

[0060] The detection unit 41 calculates the deflection, curvature, and angle of the cable 10 based on the shape of the target region R1s, and generates cable status information showing the calculation results. The detection unit 41 transmits the generated cable status information to the alarm device 121.

[0061] [Operation Flow] Figure 13 is a flowchart illustrating an example of the operation procedure when the detection device according to the embodiment of this disclosure detects a cable appearing in an captured image.

[0062] Referring to Figure 13, first, the detection device 101 waits for imaging information from the imaging device 111 (NO in step S11), and when it receives imaging information from the imaging device 111 (YES in step S11), it generates an extracted image P1 by extracting a predetermined portion in which the cable 10 is visible from the image indicated by the imaging information (step S12).

[0063] Next, the detection device 101 generates a two-tone binarized image P2 in which pixels in the target region R whose density value is less than or equal to the threshold ThA are converted to white, and pixels whose density value is greater than the threshold ThA are converted to black (step S13).

[0064] Next, the detection device 101 detects the center line of the target region R in the binarized image P2 (step S14).

[0065] Next, the detection device 101 detects the contour line of the target region R in the binarized image P2 (step S15).

[0066] Next, the detection device 101 performs a determination process to determine whether the target area R is a cable 10 based on the variation in the distance d between the center line of the target area R and the contour line of the target area R. For example, if the detection device 101 determines that the target area R is a cable 10, it determines whether the target area R is the cable 10 to be detected based on the length of the target area R (step S16).

[0067] Next, if the detection device 101 determines that the target region R1 is the cable 10 to be detected has a branch, it performs a branch removal process to remove the branch, thereby generating an image that includes the target region R1s from which the branch has been removed (step S17).

[0068] Next, the detection device 101 calculates the amount of deflection, curvature, and angle of the cable 10 based on the shape of the target region R1s, and generates cable condition information showing the calculation results (step S18).

[0069] Next, the detection device 101 transmits cable status information to the alarm device 121 (step S19).

[0070] Next, the detection device 101 awaits new imaging information from the imaging device 111 (NO in step S11).

[0071] Note that the order of steps S14 and S15 described above is not limited to the above; the order may be reversed.

[0072] Furthermore, in the detection device 101 according to the embodiment of this disclosure, the generation unit 11 is configured to generate an extracted image P1 and a binarized image P2 in which the target region R and the region other than the target region R are separated in the extracted image P1, but the invention is not limited to this configuration. The generation unit 11 may also be configured to generate a binarized image P2 in which the target region R and the region other than the target region R are separated in the captured image indicated by the imaging information received from the imaging device 111, without generating an extracted image P1. Alternatively, instead of generating a binarized image P2, the generation unit 11 may be configured to acquire the binarized image P2 from a device outside the detection device 101.

[0073] Furthermore, although the detection device 101 according to the embodiment of this disclosure is configured to detect the cable 10 that appears in the captured image, it is not limited to this configuration. The detection device 101 may also be configured to detect a tube that appears in the captured image instead of the cable 10.

[0074] Furthermore, in the detection device 101 according to the embodiment of this disclosure, the detection unit 41 is configured to determine whether or not the target region R in the binarized image P2 is the cable 10 in the determination process, but it is not limited to this. The detection unit 41 may be configured to determine whether or not there is a possibility that the target region R in the binarized image P2 is the cable 10 in the determination process, or it may be configured to quantify the possibility that the target region R in the binarized image P2 is the cable 10.

[0075] Furthermore, in the detection device 101 according to the embodiment of this disclosure, the detection unit 41 is configured to perform a determination process for the target region R based on the distance d between the center line of the target region R and the contour line of the target region R, but it is not limited to this. The detection unit 41 may be configured to perform a determination process based on the respective positions of the center line and contour line in the extracted image P1 instead of the distance d.

[0076] Furthermore, in the detection device 101 according to the embodiment of this disclosure, the detection unit 41 is configured to determine whether or not the target area R is a cable 10 based on the result of comparing the variation in the distance d between the center line and the contour line of the target area R with a threshold Th1, but it is not limited to this. For example, the detection unit 41 may be configured to perform a determination process to determine whether or not the target area R is a cable 10 based on the result of comparing the distance d with a predetermined threshold set based on the radius of the cable 10 to be detected.

[0077] Furthermore, in the detection device 101 according to the embodiment of this disclosure, the detection unit 41 is configured to determine that a target region R is a cable 10 when the variation in distance d in the target region R is less than or equal to a threshold Th1, but the invention is not limited to this configuration. For example, the detection unit 41 may be configured to determine that the target region R with the smallest variation in distance d among a plurality of target regions R in the binarized image P2 is a cable 10.

[0078] Furthermore, in the detection device 101 according to the embodiment of this disclosure, the detection unit 41 is configured to determine whether or not the target area R is the cable 10 to be detected based on the length of the target area R, but the invention is not limited to this configuration. The detection unit 41 may also be configured to determine whether or not the target area R is the cable 10 to be detected based on the distance d, regardless of the length of the target area R.

[0079] Furthermore, in the detection device 101 according to the embodiment of this disclosure, the detection unit 41 is configured to determine that a target area R with a length less than the threshold Th2 is not the cable 10 to be detected, but it is not limited to this. Depending on the purpose of the monitoring system 201, the detection unit 41 may be configured to determine that a target area R with a length of Th2 or more is not the cable 10 to be detected, while a target area R with a length less than the threshold Th2 is the cable 10 to be detected. This makes it possible to detect the cut cable 10 that appears in the captured image and determine whether the cut length of the cable 10 is appropriate, for example, when the end of the cable 10 is cut short before the transport of the cable 10 by the transport device 141 begins.

[0080] Furthermore, although the detection device 101 according to the embodiment of this disclosure is configured such that the detection unit 41 performs branch removal processing, it is not limited to this configuration. The detection unit 41 may also be configured to generate cable state information based on the shape of the target region R without performing branch removal processing when the target region R determined to be a cable 10 has a branch.

[0081] Furthermore, in the detection device 101 according to the embodiment of this disclosure, the generation unit 11 compares the density value of each pixel in the extracted image P1 with a threshold ThA, and based on the comparison result, generates a binarized image P2 in which pixels with a density value less than or equal to the threshold ThA are converted to white, and pixels with a density value greater than the threshold ThA are converted to black. However, the invention is not limited to this configuration. The generation unit 11 may also be configured to generate the binarized image P2 based on the detection result of the position of the cable 10 by a sensor (not shown) located outside the detection device 101. For example, the generation unit 11 identifies a region in the extracted image P1 in which the cable 10 is visible, based on the detection result of the position of the cable 10 by the sensor. The generation unit 11 generates a binarized image P2 in which pixels with a density value less than or equal to the threshold ThA in the identified region are converted to white, pixels with a density value greater than the threshold ThA in the identified region are converted to black, and pixels in regions other than the identified region are converted to black.

[0082] The embodiments described above should be considered in all respects to be illustrative and not restrictive. The scope of the present invention is indicated by the claims rather than the above description, and all modifications within the meaning and scope equivalent to the claims are intended to be included.

[0083] Each process (each function) of the above-described embodiment is implemented by a processing circuit (Circuitry) including one or more processors. The processing circuit may consist of one or more memories, various analog circuits, various digital circuits, etc., in addition to the one or more processors, as well as an integrated circuit. The one or more memories store programs (instructions) that cause the one or more processors to execute each of the above processes. The one or more processors may execute each of the above processes according to the programs read from the one or more memories, or they may execute each of the above processes according to logic circuits that have been pre-designed to execute each of the above processes. The processors may be various processors suitable for computer control, such as a CPU (Central Processing Unit), GPU (Graphics Processing Unit), DSP (Digital Signal Processor), FPGA (Field Programmable Gate Array), and ASIC (Application Specific Integrated Circuit). Furthermore, the physically separated multiple processors may cooperate with each other to execute each of the above processes. For example, the processors installed in each of several physically separated computers may cooperate with each other via a network such as a LAN (Local Area Network), WAN (Wide Area Network), and the Internet to perform the above processes. The program may be installed in the memory via the network from an external server device, or it may be distributed on a recording medium such as a CD-ROM (Compact Disc Read Only Memory), DVD-ROM (Digital Versatile Disk Read Only Memory), and semiconductor memory, and then installed in the memory from the recording medium.

[0084] The above description includes the following features. [Note 1] A detection device for detecting linear objects in an image, An acquisition unit that acquires a binarized image in which a target region satisfying predetermined conditions and a region other than the target region are separated in the aforementioned image, A centerline detection unit detects the centerline of the target region in the binarized image acquired by the acquisition unit, A contour detection unit that detects the contour lines of the target region in the binarized image, The system includes a determination unit that performs a determination process to determine whether the target area is a linear object based on the center line detected by the center line detection unit and the contour line detected by the contour line detection unit, The acquisition unit compares the density value of each pixel in the image with a threshold value, and generates the binarized image by converting the density value of each pixel in the image based on the comparison result. The centerline detection unit is a detection device that detects the centerline by performing a thinning process to thin the target region in the binarized image.

[0085] [Note 2] A detection device for detecting linear objects in an image, Equipped with a processing circuit, The aforementioned processing circuit is A binarized image is obtained in which the target region satisfying predetermined conditions and the region other than the target region are separated in the aforementioned image. The center line of the target region in the acquired binarized image is detected, The contour lines of the target region in the binarized image are detected, A detection device that performs a determination process to determine whether the target area is a linear object based on the detected center line and the detected contour line. [Explanation of Symbols]

[0086] 10 Cables 11 Generation part 21 Centerline detection unit 31 Contour detection unit 41 Detection unit 51 Storage section 101 Detection device 111 Imaging device 121 Alarm device 131 Dispensing device 141 Conveying device 201 Monitoring System P1 Extracted Image P2 binarized image R1,R2,R3,R4,R,R1s Target area d distance S1, S2, S3 segments

Claims

1. A detection device for detecting linear objects in an image, An acquisition unit that acquires a binarized image in which a target region satisfying predetermined conditions and a region other than the target region are separated in the aforementioned image, A centerline detection unit detects the centerline of the target region in the binarized image acquired by the acquisition unit, A contour detection unit that detects the contour lines of the target region in the binarized image, The system includes a determination unit that performs a determination process to determine whether the target area is a linear object based on the center line detected by the center line detection unit and the contour line detected by the contour line detection unit, The determination unit is a detection device that performs the determination process based on the distance between the center line and the contour line.

2. The detection device according to claim 1, wherein the determination unit performs the determination process based on the variation in distance.

3. The detection device according to claim 2, wherein the determination unit determines that the target area is the linear object when the variation is less than or equal to a predetermined value.

4. The detection device according to any one of claims 1 to 3, wherein the determination unit further determines whether the target area is the linear object to be detected based on the length of the target area.

5. The detection device according to claim 4, wherein the determination unit determines that the target region whose length is less than a predetermined value is not the linear object to be detected.

6. The detection device further, The detection device according to any one of claims 1 to 3, further comprising a removal unit that generates an image including the target region from which the branching portion has been removed, if the target region determined by the determination unit to be a linear object has a branching portion.

7. The detection device according to any one of claims 1 to 3, wherein the acquisition unit generates the binarized image based on the detection result of the position of the linear object by a sensor outside the detection device.

8. A detection method in a detection device for detecting linear objects in an image, The steps include obtaining a binarized image in which a target region satisfying predetermined conditions is separated from a region other than the target region in the aforementioned image, A step of detecting the center line of the target region in the acquired binarized image, The steps include detecting the contour lines of the target region in the binarized image, The process includes the step of determining whether the target area is a linear object based on the detected center line and contour line, A detection method in which, in the step of performing the determination process, the determination process is performed based on the distance between the center line and the contour line.

9. A detection program used in a detection device for detecting linear objects in an image, Computers, An acquisition unit that acquires a binarized image in which a target region satisfying predetermined conditions and a region other than the target region are separated in the aforementioned image, A centerline detection unit detects the centerline of the target region in the binarized image acquired by the acquisition unit, A contour detection unit that detects the contour lines of the target region in the binarized image, A determination unit performs a determination process to determine whether the target area is the linear object based on the center line detected by the center line detection unit and the contour line detected by the contour line detection unit. It is a program designed to function as such. The determination unit is a detection program that performs the determination process based on the distance between the center line and the contour line.

Images