Axle number measurement device, axle number measurement system, and axle number measurement method

Abstract

To provide an axle number measurement device, etc. which can exactly measure the number of axles of grounded tires even under the environment in which noise in an image increases, for example, at night.SOLUTION: An axile number measurement device 30 for measuring the number of axles of a vehicle 40 traveling on a road 50 comprises: a first communication unit 31 which acquires a pickup image P1 including tires of the vehicle 40; a detection unit 33 which detects the tires from the pickup image P1; a second communication unit 32 which acquires a plurality of second distances from the vehicle 40 to the road 50; and a measurement unit 34 which measures the number of axles supporting the tires in contact with the road 50 on the basis of the pickup image P1 and the plurality of second distances. The measurement unit 34 determines whether or not the tires is in contact with the road 50 on the basis of a second distance directly under the tires detected by the detection unit 33.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present disclosure relates to an axle count measuring device, an axle count measuring system, and an axle count measuring method for measuring the number of axles on a vehicle. [Background technology]

[0002] Conventionally, among vehicles with three or more axles, there are vehicles equipped with a lift axle mechanism that lifts at least one axle so that the tires on that axle are not in contact with the ground.

[0003] On the other hand, some toll roads have a toll system in which the toll fee varies depending on the number of axles of tires that are in contact with the ground while traveling.

[0004] On such toll roads, it is desirable to install an axle counting device for measuring the number of axles on which tires are in contact with the ground on traveling vehicles.

[0005] Patent document 1 discloses, as an example of an axle counting device, a vehicle type discrimination device that uses, for example, images taken with a camera to detect tires that are in contact with the road surface by taking advantage of the low brightness of the contact area between the tire and the road surface. [Prior art documents] [Patent documents]

[0006] [Patent Document 1] Japanese Patent Application Publication No. 11-86185 Summary of the Invention [Problem to be solved by the invention]

[0007] However, with the above-mentioned axle counting device, when detecting tires on the ground using images taken in an environment where noise in the images increases, such as at night, the detection accuracy decreases and the number of axles with tires on the ground cannot be accurately measured.

[0008] Therefore, an object of the present disclosure is to provide an axle number counting device, an axle number counting system, and an axle number counting method that can accurately count the number of axles of tires in contact with the ground, even in environments where noise in images increases, such as at night. [Means for solving the problem]

[0009] An axle counting device according to one embodiment of the present disclosure is an axle counting device that measures the number of axles of a vehicle traveling on a road, and includes a first acquisition unit that acquires a first captured image including tires of the vehicle, a detection unit that detects the tires from the first captured image, a second acquisition unit that acquires multiple second distances from the vehicle to the road, and a measurement unit that measures the number of axles supporting tires that are in contact with the road based on the first captured image and the multiple second distances, and the measurement unit determines whether the tire is in contact with the road based on the second distance directly below the tire detected by the detection unit.

[0010] An axle counting device according to one embodiment of the present disclosure is an axle counting device that counts the number of axles of a vehicle traveling on a road, and includes a first acquisition unit that acquires a first captured image including tires of the vehicle, a detection unit that detects the tires from the first captured image, a second acquisition unit that acquires multiple second distances from the vehicle to the road, a determination unit that determines whether the first captured image is an image captured in an environment with a predetermined level of brightness or higher, and a measurement unit that measures the number of axles based on the determination result of the determination unit, wherein the measurement unit (i) if the determination unit determines that the first captured image is an image captured in an environment with a predetermined level of brightness or higher, identifies from the first captured image whether the tires are in contact with the road and measures the number of axles based on the identification result, and (ii) if the determination unit determines that the first captured image is not an image captured in an environment with a predetermined level of brightness or higher, determines whether the tires are in contact with the road based on the second distance directly below the tires detected by the detection unit.

[0011] An axle count measurement system according to one embodiment of the present disclosure includes the above-described axle count measurement device, a first imaging device that captures the first captured image, and a second imaging device that captures images to generate the multiple second distances.

[0012] An axle number counting method according to one embodiment of the present disclosure is an axle number counting method for measuring the number of axles of a vehicle traveling on a road, and includes a first acquisition step of acquiring an image including tires of the vehicle, a detection step of detecting the tires from the image, a second acquisition step of acquiring multiple second distances from the vehicle to the road, and a measurement step of measuring the number of axles supporting tires that are in contact with the road based on the image and the multiple second distances, wherein the measurement step determines whether the tires are in contact with the road based on the detected second distances directly below the tires. [Effects of the Invention]

[0013] According to an axle number counting device according to one aspect of the present disclosure, the number of axles of tires in contact with the ground can be accurately counted even in an environment where noise in images increases, such as at night. [Brief explanation of the drawings]

[0014] [Figure 1A] FIG. 1A is a diagram showing a schematic configuration of an axle number measurement system according to the first embodiment. [Figure 1B] FIG. 1B is a diagram illustrating an example of installation of the imaging device according to the first embodiment. [Figure 2] FIG. 2 is a block diagram showing a functional configuration of the axle number measurement system according to the first embodiment. [Figure 3] FIG. 3 is a sequence diagram showing the operation of the axle number measurement system according to the first embodiment. [Figure 4] FIG. 4 is a diagram showing an example of a captured image according to the first embodiment. [Figure 5] FIG. 5 is a diagram showing an example of a distance image according to the first embodiment. [Figure 6]FIG. 6 is a flowchart showing the operation of the axle number counting device according to the first embodiment. [Figure 7] FIG. 7 is a diagram for explaining a determination as to whether or not the tire is in contact with the road according to the first embodiment. [Figure 8] FIG. 8 is a block diagram showing a functional configuration of an axle number measurement system according to a modification of the first embodiment. [Figure 9] FIG. 9 is a flowchart showing the operation of the axle number counting device according to the modified example of the first embodiment. [Figure 10] FIG. 10 is a block diagram showing a functional configuration of an axle number measurement system according to the second embodiment. [Figure 11] FIG. 11 is a flowchart showing the operation of the axle number counting device according to the second embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0015] (Summary of the Disclosure) A camera that captures images for measuring the number of axles on a vehicle is installed, for example, near a toll booth on a highway. Road lights and other similar devices are installed near the toll booth, providing a certain level of brightness on the road. When a camera captures an image of a vehicle at night or other such conditions, the amount of light near the road is low, resulting in an image with a high proportion of noise. When detecting whether a tire is on the ground using an image containing such noise, it is difficult to accurately determine whether the tire is on the ground.

[0016] Furthermore, when photographing a vehicle with a camera at night, the amount of light from the road lamps is low near the road, so the exposure time is long. For example, the exposure time at night is longer than the exposure time during the day. As a result, the resulting image is a blurred image in which the vehicle leaves a trail. For example, the image is a blurred image in which the tires leave a trail. A blurred image is an example of an image containing noise.

[0017] Although it is possible to determine whether a tire is on the ground based on whether the tire is rotating, it is difficult to accurately determine whether the tire is rotating in a video containing two or more blurred images such as those described above. In other words, it is difficult to accurately detect whether the tire is on the ground.

[0018] Therefore, the inventors have conducted extensive research into an axle counting device that can accurately count the number of axles with grounded tires even in environments where noise in images increases, such as at night, and have devised the axle counting device described below. Note that, hereinafter, tires that are in contact with the road will also be referred to as grounded tires.

[0019] An axle counting device according to one embodiment of the present disclosure is an axle counting device that measures the number of axles of a vehicle traveling on a road, and includes: a first acquisition unit that acquires a first captured image including tires of the vehicle; a detection unit that detects the tires from the first captured image; a second acquisition unit that acquires a distance image including a plurality of first distances from a predetermined position to the tire and a plurality of second distances from the predetermined position to a position outside the tire in the first captured image, the position being below the tire; and a measurement unit that counts the number of axles supporting the tire in contact with the road based on the continuity of the plurality of first distances and the plurality of second distances arranged in a line from the tire to the outside of the tire.

[0020] As a result, the axle number counting device according to one aspect of the present disclosure can count the number of axles supporting ground-contact tires using the distance image, and can therefore accurately count the number of ground-contact tire axles even in an environment where noise in the first captured image increases, such as at night. Note that the measurement unit can obtain the tire position in the distance image from the tire position in the first captured image.

[0021] Furthermore, for example, if the first captured image is an image captured in an environment with a predetermined level of brightness or higher, the measurement unit further determines from the first captured image whether or not the tire is in contact with the road, and if the first captured image is an image captured in that environment, it measures the number of axles based on the determination result.

[0022] In an environment with a certain level of brightness or higher, external light may be incident on the imaging device that measures distances to generate a distance image. When external light is incident on the imaging device, the generated distance image contains noise due to the external light. Therefore, when measuring the number of axles using a distance image containing noise due to external light, the number of axles on the ground cannot be accurately measured.

[0023] On the other hand, an axle counting device according to one aspect of the present disclosure counts the number of axles of tires on the ground using a first captured image that is less affected by noise, without using a distance image that includes noise due to external light, and can therefore accurately count the number of axles of tires on the ground even in an environment with a predetermined level of brightness or higher. Note that when the first captured image is captured in an environment with a predetermined level of brightness or higher, such as during the day, the influence of noise due to the subject being dark is reduced. In other words, the number of axles of tires on the ground can be more accurately counted from a first captured image captured in an environment with a predetermined level of brightness or higher.

[0024] Also, for example, the measurement unit measures the continuity based on an amount of change from the first distance to the second distance in the tire.

[0025] As a result, an axle number counting device according to one embodiment of the present disclosure can measure that there is continuity between the first distance and the second distance when the change from the first distance to the second distance is less than a predetermined value, and can measure that the axle is supporting the tire in contact with the road, thereby enabling more accurate measurement of the number of axles.

[0026] Also, for example, when the second distance of the tire changes from the first distance to the second distance, the measurement unit determines that the tire is not in contact with the road if the second distance is greater than the first distance by a predetermined amount.

[0027] This allows the measurement unit to determine whether the tire is in contact with the road using the predetermined amount. By appropriately setting the predetermined amount, the measurement unit can easily and accurately determine whether the tire is in contact with the road.

[0028] Also, for example, the distance image includes the first distance and the second distance measured by a TOF (Time Of Flight) method.

[0029] As a result, an axle counting device according to one aspect of the present disclosure can acquire accurate distance images even in environments where noise in images increases, such as at night.

[0030] Also, for example, the second acquisition unit acquires a second captured image including the tire captured from a viewpoint different from that of the first captured image, and generates the distance image based on the first captured image and the second captured image.

[0031] As a result, an axle counting device according to an embodiment of the present disclosure can obtain a distance image (e.g., a distance image including a first distance and a second distance) using two captured images. Furthermore, the distance image can be generated using, for example, an existing imaging device, without installing a new TOF camera or the like to generate the distance image.

[0032] In addition, an axle counting device according to one embodiment of the present disclosure is an axle counting device that measures the number of axles of a vehicle traveling on a road, and includes a first acquisition unit that acquires a first captured image including tires of the vehicle, a detection unit that detects the tires from the first captured image, and if the first captured image is an image captured in an environment with a predetermined level of brightness or higher, identifies from the first captured image whether the tires are in contact with the road, and counts the number of axles based on the identification result.

[0033] The first captured image captured in an environment with a certain level of brightness or higher is less susceptible to noise caused by a dark subject. In other words, the number of axles with ground-contact tires can be accurately measured from the first captured image captured in an environment with a certain level of brightness or higher.

[0034] For example, a distance image acquired in an environment with a certain level of brightness (e.g., a distance image acquired using a TOF method) contains noise due to external light. Therefore, when measuring the number of axles using a distance image containing noise due to external light, the number of axles with ground-contact tires cannot be accurately measured.

[0035] Therefore, as described above, by using the first captured image captured in an environment with a brightness level above a predetermined level, the number of axles of ground-contact tires can be measured more accurately than when using a distance image acquired in an environment with a brightness level above a predetermined level.

[0036] In addition, an axle count measurement system according to one aspect of the present disclosure includes the above-described axle count measurement device, a first imaging device that captures the first captured image, and a second imaging device that captures the image to generate the distance image.

[0037] This allows the number of axles with ground-contacting tires to be measured using the first captured image and distance image from the first and second imaging devices provided in the system, without having to obtain captured images from an external source.

[0038] In addition, an axle number counting method according to one aspect of the present disclosure is an axle number counting method for measuring the number of axles of a vehicle traveling on a road, and includes a first acquisition step of acquiring an image including tires of the vehicle, a detection step of detecting the tires from the image, a second acquisition step of acquiring a distance image including a plurality of first distances from a predetermined position to the tires and a plurality of second distances from the predetermined position to positions outside the tire in the image, below the tires, and a measurement step of measuring the number of axles supporting the tires in contact with the road based on the continuity of the plurality of first distances and the plurality of second distances arranged in order of positions from the tire to the outside of the tire.

[0039] This provides the same effect as the above-mentioned axle number counting device.

[0040] These general or specific aspects may be realized as a system, a method, an integrated circuit, a computer program, or a non-transitory recording medium such as a computer-readable CD-ROM, or as any combination of the system, method, integrated circuit, computer program, or recording medium. The program may be pre-stored in the recording medium, or may be supplied to the recording medium via a wide area communication network including the Internet.

[0041] Hereinafter, the embodiments will be described in detail with reference to the drawings. Note that the embodiments described below are all comprehensive or specific examples. The numerical values, shapes, materials, components, component placement and connection forms, steps, and step order shown in the following embodiments are merely examples and are not intended to limit the present disclosure. Furthermore, among the components in the following embodiments, components that are not described in the independent claims that represent the highest concept will be described as optional components.

[0042] It should be noted that the drawings are schematic diagrams and are not necessarily strict illustrations. In addition, in the drawings, substantially the same components are denoted by the same reference numerals, and overlapping descriptions may be omitted or simplified.

[0043] Furthermore, in this specification, terms indicating relationships between elements, such as identical and perpendicular, and numerical values ​​are not expressions that only express a strict meaning, but also expressions that include a substantially equivalent range, for example, a difference of a few percent.

[0044] In the following description, an image is, for example, a still image, but may also be a moving image. Also, an image is, for example, a color image, but may also be a monochrome image.

[0045] (Embodiment 1) In this embodiment, as one aspect of the present disclosure, an axle number measurement device or the like is described that measures the number of axles of ground-contact tires on a vehicle with lifted axles, using an image obtained by an imaging device capturing an image of a subject and a distance image obtained by another imaging device capturing an image of the subject.

[0046] [1-1.Configuration] First, the configuration of an axle counting system 1 including an axle counting device 30 according to this embodiment will be described with reference to Figs. 1A to 2. Fig. 1A is a schematic diagram showing the configuration of the axle counting system 1 according to this embodiment. Fig. 1B is a diagram showing an example of installation of an imaging device according to this embodiment. Fig. 2 is a block diagram showing the functional configuration of the axle counting system 1 according to this embodiment.

[0047] 1A to 2, the axle number counting system 1 includes a first imaging device 10, a second imaging device 20, and an axle number counting device 30. The axle number counting system 1 is an information processing system for counting the number of axles of ground-contact tires of a vehicle 40 traveling on a road 50.

[0048] The first imaging device 10 and the second imaging device 20 capture images of a vehicle 40 traveling on a road 50 from the side of the vehicle 40. The first imaging device 10 and the second imaging device 20 are installed on the road 50 (or on the side of the road) so as to capture images of the same area, for example. The first imaging device 10 and the second imaging device 20 may capture images of the vehicle 40 at the same angle of view, for example. Furthermore, the first imaging device 10 and the second imaging device 20 may be installed close to each other, for example. In this embodiment, the first imaging device 10 and the second imaging device 20 are installed adjacent to each other along the road 50 on which the vehicle 40 travels.

[0049] The first imaging device 10 has an image sensor and captures one or more images (see captured image P1 shown in FIG. 4, described later) including one or more tires of a vehicle 40 traveling on a road 50. The image sensor has, for example, an imaging element. The imaging element may be, for example, a solid-state imaging element such as a CMOS (Complementary Metal Oxide Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor. The first imaging device 10 is realized, for example, by a camera (for example, a visible light camera). The captured image is, for example, a visible light image.

[0050] The second imaging device 20 has a distance sensor and acquires one or more distance images (see distance image P2 shown in FIG. 5, described later) including one or more tires of a vehicle 40 traveling on a road 50. The distance sensor has a light-emitting element and a light-receiving element. In other words, the second imaging device 20 is an imaging device different from the first imaging device 10. In this embodiment, the distance sensor acquires distance images using a time-of-flight (TOF) method, which measures the time between when light is emitted from the light-emitting element and when it is received by the light-receiving element and converts the time difference into distance. However, the method for acquiring distance images is not limited to this. For example, the distance sensor may acquire distance images using a triangulation method, which uses a position-sensitive detector (PSD) as the light-receiving element and converts the change in the imaging position of the light-receiving element with a change in distance into distance. The second imaging device 20 is realized, for example, by a TOF distance imaging camera, but is not limited to this.

[0051] The distance image includes a first distance between the second imaging device 20 and each of the one or more tires of the vehicle 40, and a second distance between the second imaging device 20 and the road 50. The second distance can also be said to be the distance from the second imaging device 20 to the road surface. The one or more tires of the vehicle 40 imaged by the second imaging device 20 include the one or more tires imaged by the first imaging device 10.

[0052] Each of the first imaging device 10 and the second imaging device 20 may have a timer device that measures the current date and time, for example. The timer device is realized by a real-time clock, for example.

[0053] As described above, the first imaging device 10 and the second imaging device 20 obtain different information from each other by imaging.

[0054] An example of installation of the first imaging device 10 and the second imaging device 20 will now be described with reference to Fig. 1B. Fig. 1B is a view of the vehicle 40 as seen from the front side. Note that Fig. 1B only shows the second imaging device 20, but the same can be said for the first imaging device 10.

[0055] 1B, the second imaging device 20 is installed at a predetermined angle θ with respect to the road 50. The angle θ is, for example, an angle at which the axle number counting device 30 can acquire a distance image that enables the number of axles of the tires on the ground to be measured. The angle θ is, for example, the angle between the road 50 and the optical axis J of the second imaging device 20 when viewed from the front of the vehicle 40. The second imaging device 20 is fixed in an orientation such that the optical axis J passes through the contact point between the tires on the ground and the road 50 or near the installation location.

[0056] The angle θ is, for example, 60° or less, more preferably 45° or less, and even more preferably 30° or less. The second imaging device 20 may be installed on the road 50 (on the road surface) where the angle θ is 0°, but from the viewpoint of preventing sand, dust, and other objects from adhering, it is preferable to install it at a height of a predetermined value or more relative to the road 50. Therefore, the angle θ may be, for example, 5° or more, more preferably 10° or more, and even more preferably 15° or more. The predetermined value may be, for example, 50 cm, more preferably 100 cm, and even more preferably 150 cm.

[0057] The angle θ of the first imaging device 10 and the angle θ of the second imaging device 20 may be different from each other.

[0058] As shown in Figures 1A and 2, the axle number measurement device 30 is an information processing device that determines whether or not the tires of a vehicle 40 are on the ground based on the image captured by the first imaging device 10 and the distance image captured by the second imaging device 20, counts the number of axles of the tires on the ground, and outputs the measurement results.

[0059] 2, the axle number counting device 30 has a first communication unit 31, a second communication unit 32, a detection unit 33, and a measurement unit 34. The axle number counting device 30 is realized, for example, by a computer (not shown) including a microprocessor (not shown) and a memory (not shown), in which the microprocessor executes a program stored in the memory.

[0060] The first communication unit 31 is a communication circuit (in other words, a communication module) that enables the axle number measurement device 30 to communicate with the first imaging device 10. The first communication unit 31 acquires, for example, captured images from the first imaging device 10. The first communication unit 31 is an example of a first acquisition unit.

[0061] The second communication unit 32 is a communication circuit (in other words, a communication module) that enables the axle number counting device 30 to communicate with the second imaging device 20. The second communication unit 32, for example, acquires a distance image from the second imaging device 20. The second communication unit 32 is an example of a second acquisition unit.

[0062] Each of the first communication unit 31 and the second communication unit 32 is, for example, a wireless communication circuit for performing wireless communication, but may also be a wired communication circuit for performing wired communication. There are no particular limitations on the communication standard used for communication performed by the first communication unit 31 and the second communication unit 32. Furthermore, the first communication unit 31 and the second communication unit 32 may be configured by a single communication circuit.

[0063] The detection unit 33 detects one or more tires from one or more captured images acquired from the first imaging device 10. The method of tire detection by the detection unit 33 is not particularly limited, and conventional technology may be used. For example, the detection unit 33 may perform tire detection by performing machine learning related to tire recognition in advance. In other words, the detection unit 33 may perform tire detection by using a trained model related to tire recognition. Furthermore, the detection unit 33 may perform tire detection by using, for example, a template matching method.

[0064] The detection unit 33 can obtain information indicating the position of each of the one or more tires by detecting one or more tires. The information indicating the position of the tire may be a position on the captured image (for example, a pixel position). The position of the tire may be the center position of the tire or an area where the tire is present.

[0065] The detection unit 33 may further detect the wheels for each of the one or more detected tires. The method for detecting the wheels by the detection unit 33 is not particularly limited, as is the method for detecting the tires, and conventional technology may be used.

[0066] The detection unit 33 can obtain information indicating the position of each of the one or more wheels by detecting the one or more wheels, for example. The information indicating the position of the wheel may be a position on the captured image. The position of the wheel may be the center position of the wheel or an area in which the wheel is located.

[0067] The measurement unit 34 counts the number of axles supporting tires (ground-contact tires) on the vehicle 40 that are in contact with the road 50, based on position information indicating the positions of each of the one or more tires detected by the detection unit 33 and the distance image from the second imaging device 20. The measurement unit 34 determines whether a tire is in contact with the road 50 based on the position information and the distance image, and counts the number of axles for tires determined to be in contact. The measurement unit 34 determines whether a tire is in contact with the road 50, for example, based on the continuity between a plurality of first distances to the tire's position in the distance image and a plurality of second distances to a position outside the tire and below the tire in the captured image P1, and counts the number of axles for tires determined to be in contact. The first distance and the second distance are acquired from the distance image. The measurement unit 34 determines whether a tire is in contact with the road 50 based on, for example, the amount of change from the first distance to the second distance, and counts the number of axles for tires determined to be in contact.

[0068] [1-2. Operation] Next, the operation of the above-described axle number measurement system 1 will be described with reference to Figures 3 to 7. Figure 3 is a sequence diagram showing the operation of the axle number measurement system 1 according to this embodiment.

[0069] As shown in Fig. 3, the first imaging device 10 images the vehicle 40 (S11) and outputs the image obtained by imaging to the axle number counting device 30 (S12). The second imaging device 20 also images the vehicle 40 (S21) and outputs the distance image obtained by imaging to the axle number counting device 30 (S22). In step S21, the light-emitting element of the second imaging device 20 emits pulsed light, and the light-receiving element of the second imaging device 20 receives the reflected light of the pulsed light reflected by an object. The calculation unit of the second imaging device 20 performs calculations to convert the time difference between emitting the pulsed light and receiving the reflected light into distance. This results in a distance image.

[0070] The area imaged in step S11 and the area imaged in step S21 are areas that include one or more tires of the vehicle 40, and may be, for example, the same area. The area imaged in step S11 and the area imaged in step S21 may each be the dashed area IV shown in FIG. 1A.

[0071] The captured image output in step S12 and the distance image output in step S22 may be images captured at the same time. The images captured at the same time may be images obtained by performing imaging operations at the same timing when the imaging timings of the first imaging device 10 and the second imaging device 20 are synchronized. Alternatively, the first imaging device 10 and the second imaging device 20 may constantly capture images, and the images captured at the same time may be images obtained by clipping the images captured at the same time.

[0072] Next, the axle number counting device 30 acquires captured images from the first imaging device 10 and acquires distance images from the second imaging device 20 (S31). Specifically, the first communication unit 31 of the axle number counting device 30 acquires captured images from the first imaging device 10, and the second communication unit 32 of the axle number counting device 30 acquires distance images from the second imaging device 20. The timing of acquiring the captured images and the distance images may be the same or different. Step S31 is an example of a first acquisition step and a second acquisition step.

[0073] The captured image and distance image will now be described with reference to Figs. 4 and 5. Fig. 4 is a diagram showing an example of a captured image P1 according to this embodiment. Fig. 5 is a diagram showing an example of a distance image P2 according to this embodiment. Note that Figs. 4 and 5 are images of the dashed-line area IV shown in Fig. 1A. In Fig. 5, the distance from the second imaging device 20 is shown in grayscale, with closer objects being whiter and farther objects being blacker.

[0074] As shown in FIGS. 4 and 5, the axle number counting device 30 acquires a captured image P1 and a distance image P2 that include rear tires 41 and 42 on a rear axle of a vehicle 40. The captured image P1 is an example of a first captured image. The distance image P2 is formed based on a distance measured from a predetermined position. The predetermined position is, for example, the position where the second imaging device 20 is installed, but is not limited to this. The predetermined position may also be, for example, the position where the first imaging device 10 is installed. In this case, the distance of the distance image captured by the second imaging device 20 is corrected according to the difference in the installation positions of the first imaging device 10 and the second imaging device 20.

[0075] In step S31, the first communication unit 31 may acquire from the first imaging device 10 a captured image P1 that includes the front tire 43 of the front axle of the vehicle 40 and the rear tires 41 and 42 of the rear axle of the vehicle 40. In step S31, the second communication unit 32 may acquire from the second imaging device 20 a distance image P2 that includes the front tire 43 of the front axle of the vehicle 40 and the rear tires 41 and 42 of the rear axle of the vehicle 40.

[0076] The first communication unit 31 outputs the acquired captured image P1 to the detection unit 33. The second communication unit 32 outputs the acquired distance image P2 to the measurement unit .

[0077] Referring again to FIG. 3, the detection unit 33 detects one or more tires from the acquired captured image P1 (S32). In the example of FIG. 4, the detection unit 33 detects rear tire 41 and 42. The detection unit 33 detects, for example, a tire region R1 indicating the position of the rear tire 41 and a tire region R2 indicating the position of the rear tire 42. The detection unit 33 may also detect the position of each wheel of one or more tires from the acquired captured image P1. The rear tire 41 and 42 are an example of one or more tires. Step S32 is an example of a detection step.

[0078] It should be noted that tires can be detected even in the captured image P1 captured in an environment where the influence of noise is significant, such as at night. For example, the area around the road 50 is illuminated by lights such as street lamps, so the first imaging device 10 can capture the captured image P1 with a quality that allows tires to be detected.

[0079] The detection unit 33 outputs position information indicating the positions of the one or more detected tires to the measurement unit 34. In the example of Fig. 4, the detection unit 33 outputs information indicating tire regions R1 and R2 to the measurement unit 34 as position information.

[0080] The measurement unit 34 counts the number of axles based on the distance image P2 (S33). Specifically, the measurement unit 34 identifies the position of one or more tires in the distance image P2 based on the position information acquired from the detection unit 33, determines whether or not each of the identified one or more tires is in contact with the road 50, and counts the number of axles of the ground-contacting tires based on the determination result. Note that a method for determining whether or not a tire is in contact with the road 50 will be described later. Step S33 is an example of a measurement step.

[0081] Next, the measuring unit 34 outputs the number of axles measured in step S33 (S34). The measuring unit 34 may output the number of axles to an external device, or, if the axle number measuring device 30 has a display unit such as a display, may cause the display unit to display the number of axles. The number of axles measured by the measuring unit 34 is an example of a measurement result.

[0082] Next, the operation of the axle number counting device 30 will be described with reference to Fig. 6. Fig. 6 is a flowchart showing the operation of the axle number counting device 30 according to this embodiment.

[0083] 6, the axle number measurement device 30 acquires a captured image P1 and a distance image P2 (S101). The captured image P1 is output to the detection unit 33. The distance image P2 is output to the measurement unit 34. Step S101 corresponds to step S31 shown in FIG. 3.

[0084] Next, the detection unit 33 detects one or more tires from the captured image P1 (S102). The detection unit 33, for example, identifies the positions of each of the one or more tires from the captured image P1. The detection unit 33 outputs position information indicating the positions of the one or more detected tires to the measurement unit 34. Step S102 corresponds to step S32 shown in FIG. 3.

[0085] Next, the measurement unit 34 identifies the positions of one or more tires in the distance image P2 based on the position information acquired from the detection unit 33 (S103). In this embodiment, the captured image P1 and the distance image P2 are images of the same area (e.g., the dashed-line area IV). Therefore, the tire positions in the captured image P1 and the tire positions in the distance image P2 are the same. Therefore, the measurement unit 34 superimposes the tire regions R1 and R2 included in the position information on the distance image P2, as shown in FIG. 5, for example.

[0086] In this way, the measurement unit 34 identifies the positions of one or more tires in the distance image P2 based on the position information acquired from the detection unit 33. In this embodiment, the captured image P1 is used to identify the positions of one or more tires in the distance image P2. In other words, in this embodiment, the captured image P1 is not used to determine whether or not the tire is in contact with the road 50.

[0087] The measurement unit 34 may apply a predetermined correction to the position information and identify the positions of one or more tires in the distance image P2 based on the corrected position information. Applying a predetermined correction may include, for example, correcting at least one of the position and size of the tire region R1 in the captured image P1. The measurement unit 34 may, for example, convert the tire regions R1 and R2 detected in the captured image P1 into areas on the distance image P2 corresponding to the tire regions R1 and R2, depending on the installation conditions of the first and second image capture devices 10 and 20, and then superimpose the converted tire regions R1 and R2. The installation conditions include the installation positions of the first and second image capture devices 10 and 20, the orientation of the optical axis J, and the like.

[0088] Next, the measurement unit 34 determines whether or not a tire is in contact with the road 50 based on the distance image P2 in which the positions of one or more tires have been identified (S104). In other words, the measurement unit 34 counts the number of axles of tires on the vehicle 40 that are in contact with the road 50 based on the continuity of the distance values ​​from the tires to the road 50 in the distance image P2. Specifically, the measurement unit 34 counts the number of axles of tires on the vehicle 40 that are in contact with the road 50 based on the continuity between a first distance from the second image capture device 20 to the tire in the distance image P2 and a second distance from the second image capture device 20 to a position on the road 50 below the tire that is outside the tire in the captured image P1.

[0089] The measurement unit 34 counts the number of axles supporting the tire in contact with the road 50, for example, based on the continuity of multiple first distances and multiple second distances arranged at positions from the tire to the outside of the tire.

[0090] The measurement unit 34 determines whether the tires of the vehicle 40 are in contact with the road 50 based on the continuity of the distance from the tire to the second imaging device 20 on the road 50, on a line that passes through the center of the tire and extends vertically downward when the vehicle 40 is viewed from the side, and counts the number of axles of the tire on the vehicle 40 that are in contact with the road 50. The center of the tire may be, for example, the center of the wheel.

[0091] For example, in the case of the rear tire 41, the measurement unit 34 determines whether the rear tire 41 is in contact with the road 50 based on the continuity of distance within the measurement area R3. The measurement area R3 includes, for example, a part of the rear tire 41 and an area below the tire area R1. For example, the measurement area R3 is an area that includes the center of the rear tire 41 and the road 50 below the center of the rear tire 41.

[0092] Furthermore, for example, with respect to the rear tire 42, the measurement unit 34 determines whether the rear tire 42 is in contact with the road 50 based on the continuity of distance within the measurement area R4. The measurement area R4 includes, for example, a part of the rear tire 42 and an area below the tire area R2. For example, the measurement area R4 is an area that includes the center of the rear tire 42 and the road 50 below the center of the rear tire 42.

[0093] The measurement unit 34 determines whether or not there is continuity in the distance from the tire to the road 50 in each of the measurement areas R3 and R4. FIG. 7 is a diagram for explaining the determination of whether or not the tire is in contact with the road 50 according to this embodiment. (a) of FIG. 7 is a diagram for explaining the determination of the continuity of the distance in the measurement area R3. That is, (a) of FIG. 7 shows the results of the distance measurement for determining whether or not the rear tire 41 is in contact with the road 50. Also, (b) of FIG. 7 is a diagram for explaining the determination of the continuity of the distance in the measurement area R4. That is, (b) of FIG. 7 shows the results of the distance measurement for determining whether or not the rear tire 42 is in contact with the road 50.

[0094] 7(a) and 7(b) show the measurement results of the distance from the wheel to the second imaging device 20 on the road 50, but it is sufficient to include the measurement results of at least the distance between the tire and the second imaging device 20 and the distance between the road 50 at a position immediately below the tire and the second imaging device 20. The traveling direction of the vehicle 40 is the direction perpendicular to the paper surface of FIG. 7. The distances in FIGS. 7(a) and 7(b) are the distances when the vehicle 40 is viewed from the side. "Small distance" means that the distance to the second imaging device 20 is short.

[0095] As shown in FIG. 7(a), the distance is not continuous at the boundary between the rear tire 41 and the road 50. Specifically, the distance is not continuous in the region indicated by the two-dot chain line in FIG. 7(a). A distance change d1 occurs between the lowest point of the rear tire 41 and the position directly below the rear tire 41 on the distance image P2. This is because the rear tire 41 is floating above the road 50, and the position directly below the rear tire 41 on the distance image P2 is on the road 50 that is farther away than the rear tire 41. Note that the dashed line at the boundary between the tire and the road 50 in FIG. 7(a) indicates the position of the lower dashed line (on the road 50 side) of the dashed lines that make up the tire region R1 in FIG. 5 and extend in the traveling direction of the vehicle 40. The position directly below the rear tire 41 is an example of a position adjacent to the tire in the direction of the road 50. In this embodiment, the position directly below the rear tire 41 is, for example, the road 50.

[0096] Furthermore, the position directly below the rear tire 41 in the distance image P2 may be the position of a pixel (hereinafter referred to as the directly below pixel) that is a predetermined number of pixels below the pixel corresponding to the lowest point of the rear tire 41 (hereinafter referred to as the lowest point pixel). The predetermined number of pixels may be any value that can determine that the tire has been lifted by the lift axle mechanism to such an extent that it does not come into contact with the road 50. The predetermined number of pixels may be, for example, 1. In other words, the directly below pixel may be a pixel adjacent to the lowest point pixel. Furthermore, the predetermined number of pixels may be, for example, the number of pixels that corresponds to a predetermined distance (e.g., several centimeters) from the lowest point pixel when converted into real space.

[0097] For example, when the amount of change d1 is greater than a predetermined amount, the measurement unit 34 determines that the rear tire 41 is not in contact with the road 50. In other words, the measurement unit 34 determines that the rear tire 41 is lifted up.

[0098] The predetermined amount may be any value as long as it can determine whether the rear tire 41 is in contact. The predetermined amount is determined appropriately, for example, based on the angle θ of the second imaging device 20. The predetermined amount may be, for example, larger than the recession amount d2, which is the difference between the first distance to the rear tire 41 and the third distance to the wheel. The predetermined amount may be, for example, larger than the recession amount d2 and smaller than the change amount d1.

[0099] This makes it possible to prevent erroneous determinations by the measurement unit 34 when determining whether or not the rear tire 41 is in contact with the road 50. For example, when the amount of change d1 is smaller than a predetermined amount, and the predetermined amount is smaller than the amount of recession d2, it is possible to prevent the measurement unit 34 from erroneously determining that the rear tire 41 is not in contact with the road 50 because the amount of recession d2 is larger than the predetermined value.

[0100] As shown in FIG. 7(b), the distance changes smoothly at the boundary between the rear tire 42 and the road 50. In other words, the distance is continuous at the boundary between the rear tire 42 and the road 50. For example, the distance between the lowest point of the rear tire 42 and the position directly below the rear tire 42 on the distance image P2 is the same. This is because the rear tire 42 is in contact with the road 50, and the road 50 directly below the rear tire 42 is at the same distance as the rear tire 42 on the distance image P2. Note that the dashed line at the boundary between the tire and the road 50 in FIG. 7(b) indicates the position of the lower dashed line (on the road 50 side) of the dashed lines that make up the tire region R2 in FIG. 5 and extend in the traveling direction of the vehicle 40. The position directly below the rear tire 42 is an example of a position adjacent to the tire in the road direction. In this embodiment, the position directly below the rear tire 42 is, for example, the road 50.

[0101] For example, when the distance between the rear tire 42 and the road 50 is continuous, the measurement unit 34 determines that the rear tire 42 is in contact with the road 50. In other words, the measurement unit 34 determines that the rear tire 42 is not lifted up. The measurement unit 34 may also determine that the rear tire 42 is in contact with the road 50 when the amount of change d1 shown in FIG. 7(a) is equal to or less than a predetermined amount.

[0102] In this way, the measurement unit 34 measures the continuity of distance in the tire based on the amount of change d1 from the first distance to the second distance. That is, the measurement unit 34 determines the continuity of distance in the tire based on the amount of change d1 from the first distance to the second distance.

[0103] 6 again, for example, as shown in Fig. 7(b), if a first distance to the lowest point of the rear tire 42 and a second distance to a position outside the tire region R2 and adjacent to the lowest point match, or if the change in the two distances is equal to or less than a predetermined amount, the measurement unit 34 determines that the rear tire 42 is in contact with the road 50 (Yes in S104) and counts the axle of the rear tire 42 in the number of axles of ground-contact tires (S105). If the result in step S104 is Yes, for example, the measurement unit 34 adds 1 to the number of axles of ground-contact tires.

[0104] 7(a), for example, if the change d1 between the first distance to the lowest point of the rear tire 41 and the second distance to a position outside the tire region R1 and adjacent to the lowest point is greater than a predetermined amount, the measurement unit 34 determines that the tire is not in contact with the road 50 (No in S104), and proceeds to step S106. In other words, the measurement unit 34 determines that the tire is not in contact with the road 50 if, when the first distance changes to the second distance in the distance image P2, the second distance is greater than the first distance by a predetermined amount.

[0105] Note that the measurement unit 34 is not limited to making the above determination using the first distance to the tire's lowest point. The measurement unit 34 may make the above determination using the first distance to the tire. The first distance may be, for example, the distance to the tire's outer circumference, or the distance to a position a predetermined distance inward from the tire's outer circumference. In this case, the measurement unit 34 determines that the rear tire 41 is in contact with the road 50 when the amount of change d1 between the first distance to a position other than the tire's lowest point and the second distance to a position outside the rear tire 41 that is adjacent to the rear tire's lowest point is equal to or less than a predetermined amount (Yes in S104). This is also included in determining which tire is in contact with the road 50 based on the continuity between the first distance and the second distance.

[0106] Next, if the process of step S105 has been executed or if the determination in step S104 is No, the measurement unit 34 checks whether or not all tires have been determined (S106). The measurement unit 34 determines, for example, whether or not the determination in step S104 has been executed for each of the one or more tires detected in step S102.

[0107] If all tires have been determined (Yes in S106), the measurement unit 34 outputs the number of axles (S107) and ends the process. If all tires have not been determined (No in S106), the measurement unit 34 returns to step S104 and executes the processes from step S104 onwards for the remaining tires.

[0108] Steps S103 to S106 correspond to step S33 shown in Fig. 3. Step S107 corresponds to step S34 shown in Fig. 3.

[0109] Next, if the determination in step S106 is Yes, the measurement unit 34 outputs the number of axles counted in step S105 (S107). Step S107 corresponds to step S34 shown in FIG.

[0110] As described above, axle number counting device 30 according to this embodiment includes an acquisition unit (e.g., first communication unit 31 and second communication unit 32) that acquires captured image P1 and distance image P2, a detection unit 33 that detects one or more tires based on captured image P1 in order to identify the positions of one or more tires in distance image P2, and a measurement unit 34 that counts the number of axles of ground-contact tires based on the continuity of the first distance and the second distance in distance image P2. Measurement unit 34 determines whether a tire is in contact with road 50 and counts the number of ground-contact tires from the continuity of the distance at the boundary (contact point) between the ground-contact tire and road 50 on distance image P2.

[0111] In this way, the axle number counting device 30 performs the above measurement using the distance image P2, which has less noise, in an environment where noise in the captured image P1 increases, such as at night. Therefore, the axle number counting device 30 can accurately count the number of axles of ground-contact tires even in an environment where noise in the captured image P1 increases, such as at night.

[0112] (Modification of the first embodiment) In this modified example, as one aspect of the present disclosure, an axle number measurement device or the like that measures the number of axles from a captured image P1 when a predetermined condition is satisfied will be described.

[0113] First, the configuration of an axle counting system 1a equipped with an axle counting device 30a according to this modified example will be described with reference to Fig. 8. Fig. 8 is a block diagram showing the functional configuration of the axle counting system 1a according to this modified example. Note that the same components as those in the axle counting system 1 according to embodiment 1 are denoted by the same reference numerals as those in embodiment 1, and descriptions thereof will be omitted or simplified.

[0114] 8, the axle number counting system 1a includes a first imaging device 10, a second imaging device 20, and an axle number counting device 30a. The axle number counting device 30a includes a determination unit 35 in addition to the axle number counting device 30 according to the first embodiment.

[0115] In this modification, the first imaging device 10 outputs exposure time information indicating an exposure time to the axle number counting device 30a. The timing at which the first imaging device 10 outputs the exposure time information to the axle number counting device 30a is not particularly limited. For example, the first imaging device 10 may output the captured image P1 to the axle number counting device 30a, including exposure time information indicating the exposure time used to capture the captured image P1. The first imaging device 10 may also output the exposure time information to the axle number counting device 30a at predetermined time intervals, for example. The first imaging device 10 may also output the exposure time information for the capture to the axle number counting device 30a before starting capture. For example, when the first imaging device 10 acquires information indicating that a vehicle 40 will be traveling ahead of the second imaging device 20, the first imaging device 10 may output the exposure time information to the axle number counting device 30a before the vehicle 40 travels ahead of the second imaging device 20.

[0116] The first communication unit 31 is a communication circuit (in other words, a communication module) that enables the axle number counting device 30a to communicate with the first imaging device 10. The first communication unit 31 acquires, for example, the captured image P1 and exposure time information from the first imaging device 10. The first communication unit 31 is an example of a first acquisition unit.

[0117] The determination unit 35 determines whether the captured image P1 acquired from the first imaging device 10 is an image captured in an environment with brightness equal to or higher than a predetermined value. In this embodiment, the determination unit 35 determines whether the captured image P1 is an image captured in an environment with brightness equal to or higher than a predetermined value based on the exposure time when the captured image P1 was captured by the first imaging device 10. For example, if the exposure time when the captured image P1 was captured is equal to or shorter than a predetermined time, the determination unit 35 determines that the captured image P1 is an image captured in an environment with brightness equal to or higher than a predetermined value. The predetermined time is a time during which noise due to external light does not affect detection of the ground-contact tire when the second imaging device 20 captures the image.

[0118] An environment with brightness equal to or greater than a predetermined level is, for example, an environment in which external light such as sunlight is irradiating the road 50, such as a daytime environment. An environment with brightness equal to or greater than a predetermined level may be, for example, an environment in the imaging areas of the first imaging device 10 and the second imaging device 20. It can also be said that the determination unit 35 determines whether the amount of external light irradiating the road 50 is equal to or greater than a predetermined value. The imaging area is, for example, the dashed-line area IV shown in FIGS. 4 and 5.

[0119] In this case, external light may be reflected by road 50 and enter second image capture device 20. The external light that enters may become noise in distance image P2. In other words, in an environment with brightness above a certain level, second image capture device 20 may find it difficult to measure distance accurately.

[0120] Therefore, in this modification, in addition to the processing of the first embodiment, when the determination unit 35 determines that the captured image P1 was an image captured in an environment with a predetermined level of brightness or higher, the measurement unit 34 counts the number of axles of the ground-contacting tires using only the captured image P1 out of the captured image P1 and the distance image P2. Note that external light is light other than the light emitted by the second imaging device 20, such as sunlight or illumination light.

[0121] Next, the operation of the axle number counting device 30a will be described with reference to Fig. 9. Fig. 9 is a flowchart showing the operation of the axle number counting device 30a according to this modified example. Note that the same operations as in embodiment 1 are denoted by the same reference numerals as in embodiment 1, and the description will be omitted or simplified. In addition, the following describes a case where the first imaging device 10 outputs exposure time information for imaging to the axle number counting device 30a before starting imaging.

[0122] 9, the first communication unit 31 of the axle number measurement device 30a acquires exposure time information for the captured image P1 from the first imaging device 10 (S201). The first communication unit 31 may acquire the exposure time information periodically, or may acquire the exposure time information before the vehicle 40 enters the imaging area of ​​the second imaging device 20 when the passage of the vehicle 40 is detected in advance. The first communication unit 31 outputs the exposure time information to the determination unit 35.

[0123] Next, the determination unit 35 determines whether the exposure time indicated by the exposure time information is equal to or shorter than a predetermined time (S202). Determining whether the exposure time indicated by the exposure time information is equal to or shorter than a predetermined time is an example of determining whether the captured image P1 is an image captured in an environment with brightness equal to or higher than a predetermined value. For example, the determination unit 35 determines whether the amount of external light near the road 50 is equal to or higher than a predetermined value.

[0124] If the exposure time indicated by the exposure time information is equal to or shorter than a predetermined time, the determination unit 35 determines that the captured image P1 is an image captured in an environment with brightness equal to or higher than a predetermined value (Yes in S202), and proceeds to step S203. If the exposure time indicated by the exposure time information is longer than the predetermined time, the determination unit 35 determines that the captured image P1 is not an image captured in an environment with brightness equal to or higher than a predetermined value (No in S202), and proceeds to step S101. Note that the processing from step S101 onwards is the same as that in Fig. 6 of the first embodiment, and therefore description thereof will be omitted.

[0125] In the above description, the determination unit 35 determines whether the captured image P1 is an image captured in an environment with brightness equal to or higher than a predetermined value based on exposure time information. However, this is not limiting. The determination unit 35 may perform the determination in step S202, for example, based on the captured image P1 acquired from the first imaging device 10. The determination unit 35 may perform the determination in step S202, for example, based on the pixel value of each pixel included in the captured image P1. The determination unit 35 may determine that the captured image P1 is an image captured in an environment with brightness equal to or higher than a predetermined value, for example, if the value based on the pixel value of each pixel is equal to or higher than a predetermined value. In this case, the first imaging device 10 outputs the captured image P1 to the axle number counting device 30a. The first communication unit 31 then outputs the acquired captured image P1 to both the measurement unit 34 and the determination unit 35. The value based on the pixel value of each pixel may be, for example, any of the maximum value, minimum value, average value, median value, mode value, etc. of the pixel value of each pixel, or may be the pixel value of one or more predetermined pixels, or may be a value obtained by performing a predetermined calculation on the pixel value. The captured image P1 used for making the determination in step S202 may be, for example, the captured image P1 previously acquired from the first imaging device 10.

[0126] The determination unit 35 may also acquire illuminance near the road 50 (e.g., illuminance within the imaging area of ​​the second imaging device 20) from an external illuminance sensor, and make the determination in step S202 based on the acquired illuminance. The determination unit 35 may also acquire weather information for the area where the second imaging device 20 is installed from a weather information server that manages weather information, and make the determination in step S202 based on the acquired weather information. The weather information may include, for example, temperature, rainfall, cloud cover, solar radiation, weather, and the like. The determination unit 35 may determine that the captured image P1 is an image captured in an environment with brightness equal to or greater than a predetermined value, for example, when the amount of solar radiation is equal to or greater than a predetermined value or when the weather is clear. The illuminance and weather information are acquired via, for example, at least one of the first communication unit 31 and the second communication unit 32. The determination unit 35 may also acquire the current time, and make the determination in step S202 based on the acquired current time. For example, when the current time is a time indicating daytime, the determination unit 35 may determine that the captured image P1 is an image captured in an environment with brightness equal to or higher than a predetermined level.

[0127] If the determination unit 35 determines Yes in step S202, it may output stop information to the second imaging device 20 via the second communication unit 32, indicating that imaging by the second imaging device 20 is to be stopped. This causes the second imaging device 20 to stop imaging, thereby reducing power consumption in the second imaging device 20. If the determination unit 35 determines Yes in step S202, it may output measurement control information to the measurement unit 34, indicating that the number of axles of ground-contact tires is to be measured based on the captured image P1. This makes it possible to prohibit the measurement unit 34 from measuring the number of ground-contact tire axles using the distance image P2 when the measurement unit 34 acquires the distance image P2 in the case where the determination unit 35 determines Yes in step S202.

[0128] If the determination unit 35 determines Yes in step S202, the first communication unit 31 acquires the captured image P1 from the first imaging device 10 (S203). The first communication unit 31 outputs the acquired captured image P1 to the detection unit 33.

[0129] Next, the detection unit 33 detects one or more tires from the captured image P1 (S204). For example, if the captured image P1 is an image captured in an environment with a predetermined level of brightness or higher, the detection unit 33 further identifies from the captured image P1 whether or not each of the one or more tires is in contact with the road 50. Note that the processing in step S204 is similar to step S102, and therefore a description thereof will be omitted.

[0130] Next, the measurement unit 34 determines whether or not a tire is in contact with the road 50 based on the captured image P1 in which the positions of one or more tires have been identified (S205). That is, the measurement unit 34 determines whether or not a tire is in contact with the road 50 based on the captured image P1. The method for determining whether or not a tire is in contact with the road 50 based on the captured image P1 is not particularly limited, and a conventional technique may be used. The measurement unit 34, for example, calculates a reference line extending from the lowest point of the rear tire 42 in the traveling direction of the vehicle 40. Then, for example, for a tire other than the front tire 43 and the rear tire 42 (for example, the rear tire 41), the measurement unit 34 determines whether or not the tire is in contact with the road 50 based on whether or not the lowest point of the tire is located above the vehicle 40 by a predetermined value or more from the reference line. Note that the measurement unit 34 may calculate, for example, a straight line connecting the lowest point of the front tire 43 and the lowest point of the rear tire 42 as the reference line.

[0131] Here, the predetermined value may be any value that indicates that the tires excluding the front tires 43 and the rear tires 42 are lifted by the lift axle mechanism to a degree that prevents them from contacting the road 50. The predetermined value may be, for example, a predetermined number of pixels in the captured image P1 (e.g., 1000 pixels), or the number of pixels in the captured image P1 that corresponds to a predetermined distance (e.g., 10 cm) when converted into real space.

[0132] Furthermore, the measurement unit 34 may determine whether the tire is in contact with the road 50 based on whether the tire is rotating. The measurement unit 34 may determine whether the tire is rotating based on, for example, two or more captured images P1 that are captured consecutively, and may determine that the tire is in contact with the road 50 when the tire is rotating.

[0133] If the measurement unit 34 determines that the tire is in contact with the road 50 (Yes in S205), it counts the axle of that tire in the number of axles of ground-contact tires (S206). That is, if the captured image P1 is an image captured in an environment with a predetermined level of brightness or higher, the measurement unit 34 counts the number of axles based on the identification result of the detection unit 33. For example, if the measurement unit 34 determines Yes in step S205, it adds 1 to the number of axles of ground-contact tires. If the measurement unit 34 determines that the tire is not in contact with the road 50 (No in S205), it proceeds to step S207.

[0134] Next, if the process of step S206 has been executed or if the determination in step S205 is No, the measurement unit 34 checks whether or not all tires have been determined (S207). The measurement unit 34 determines, for example, whether or not the process of step S205 has been executed for each of the one or more tires detected in step S204.

[0135] Next, if all tires have been determined (Yes in S207), the measurement unit 34 outputs the number of axles (S107) and ends the process. If all tires have not been determined (No in S207), the measurement unit 34 returns to step S205 and executes the process of step S205 for the remaining tires.

[0136] As described above, the axle number counting device 30a according to this modified example includes a determination unit 35 that determines whether the captured image P1 was captured in an environment with a predetermined level of brightness or higher. The measurement unit 34 switches the method of counting the number of axles depending on the determination result of the determination unit 35. When the determination unit 35 determines that the captured image P1 was captured in an environment with a predetermined level of brightness or higher (corresponding to Yes in S202), the measurement unit 34 counts the number of axles of ground-contact tires based on the captured image P1 (S203 to S207). When the determination unit 35 determines that the captured image P1 was not captured in an environment with a predetermined level of brightness or higher (corresponding to No in S202), the measurement unit 34 counts the number of ground-contact tires based on the distance image P2 (S101 to S107).

[0137] In this way, the axle number counting device 30a performs the above measurement using the captured image P1, which has less noise, in an environment where noise in the distance image P2 increases, such as during the daytime. Therefore, the axle number counting device 30a can accurately count the number of axles of ground-contact tires even in an environment where noise in the distance image P2 increases, such as during the daytime.

[0138] Although the above describes an example in which the process of counting the number of axles is performed based on the captured images and distance images when step S202 is No, the present invention is not limited to this. For example, when step S202 is No, the axle number counting device 30a may not perform the process of counting the number of axles. In other words, the axle number counting device 30a may perform the process of counting the number of axles using the captured images at least when step S202 is Yes.

[0139] In this way, the axle number counting device 30a may determine whether the captured image was captured in an environment with a predetermined level of brightness or higher, and if the captured image was captured in an environment with a predetermined level of brightness or higher, may count the number of axles using the captured image. In this case, the distance image is not used to count the number of axles.

[0140] (Embodiment 2) In this embodiment, as one aspect of the present disclosure, an axle number measurement device is described in which both the first imaging device and the second imaging device have image sensors, and the device uses two captured images to measure the number of axles with grounded tires on a vehicle whose axles are lifted up.

[0141] [2-1.Configuration] First, the configuration of an axle counting system 100 including an axle counting device 130 according to this embodiment will be described with reference to Fig. 10. Fig. 10 is a block diagram showing the functional configuration of the axle counting system 100 according to this embodiment. Note that the same components as those in the axle counting system 1 according to embodiment 1 are denoted by the same reference numerals as in embodiment 1, and descriptions thereof will be omitted or simplified.

[0142] As shown in FIG. 10, the axle number counting system 100 includes a first imaging device 10, a second imaging device 120, and an axle number counting device .

[0143] The configuration of the second imaging device 120 is, for example, the same as that of the first imaging device 10. Specifically, the second imaging device 120 has an image sensor and captures one or more images including one or more tires of a vehicle 40 traveling on a road 50. The image sensor has, for example, an imaging element. The imaging element can be, for example, a solid-state imaging element such as a CMOS image sensor or a CCD image sensor. The second imaging device 120 is realized, for example, by a camera (for example, a visible light camera), but is not limited to this.

[0144] Furthermore, the first imaging device 10 and the second imaging device 120 may be realized as a single device. For example, the first imaging device 10 and the second imaging device 120 may form a stereo camera. The first imaging device 10 and the second imaging device 120 may perform synchronized imaging, for example.

[0145] Furthermore, the positions at which the first imaging device 10 and the second imaging device 120 are installed, the direction of the optical axis J, and the like are fixed in advance.

[0146] The axle number counting device 130 includes a generation unit 136 in addition to the axle number counting device 30 according to the first embodiment.

[0147] The generation unit 136 acquires a captured image P1 from the first imaging device 10 via the first communication unit 31, and acquires a captured image (not shown) from the second imaging device 120 via the second communication unit 32. The captured image acquired from the second imaging device 120 is an example of a second captured image, and will hereinafter also be referred to as the second captured image.

[0148] The generation unit 136 then generates a distance image from the captured image P1 and the second captured image. While the method by which the generation unit 136 generates the distance image is not particularly limited, the distance image is generated by calculating the distance to the subject from parallax information obtained by comparing captured images captured by two imaging devices arranged at a distance from each other. The generation unit 136 is an example of a second acquisition unit that acquires the distance image by generating the distance image from the captured image P1 and the second captured image.

[0149] It should be noted that the generating unit 136 is not limited to generating a distance image from two captured images, but may generate a distance image from, for example, three or more captured images captured simultaneously.

[0150] In the above, an example has been described in which the axle count counting system 100 uses the captured image P1 for detecting tires to generate the distance image P2, but the present invention is not limited to this. The axle count counting system 100 may include, for example, three or more imaging devices. The axle count counting system 1a may include, for example, a first imaging device 10, a second imaging device 120, and a third imaging device (not shown). The axle count counting system 100 may detect tires based on an image captured by the first imaging device 10, and generate a distance image from two images captured by the second imaging device 20 and the third imaging device, respectively.

[0151] [2-2. Operation] Next, the operation of the axle number counting device 130 will be described with reference to Fig. 11. Fig. 11 is a flowchart showing the operation of the axle number counting device 130 according to this embodiment. Note that the same operations as in embodiment 1 are denoted by the same reference numerals as in embodiment 1, and the description thereof will be omitted or simplified.

[0152] 11, the axle number counting device 130 acquires a first captured image (for example, captured image P1) and a second captured image that are captured simultaneously from different viewpoints (S301). Specifically, the first communication unit 31 of the axle number counting device 130 acquires the first captured image from the first imaging device 10, and the second communication unit 32 of the axle number counting device 130 acquires the second captured image from the second imaging device 120. The timing of acquiring the first captured image and the second captured image may be the same or different.

[0153] The first communication unit 31 outputs the acquired first captured image to the detection unit 33 and the generation unit 136. The second communication unit 32 outputs the acquired second captured image to the generation unit 136.

[0154] The detection unit 33 detects one or more tires from the first captured image (S302), and outputs position information indicating the positions of the one or more detected tires to the measurement unit .

[0155] The generation unit 136 generates a distance image P2 from the acquired first captured image and second captured image (S303). Step S303 is an example of a second acquisition step.

[0156] The processes from step S103 onwards are the same as those in the first embodiment, and therefore the description thereof will be omitted.

[0157] As described above, the axle number counting device 130 according to this embodiment has the generating unit 136 that generates a distance image from two or more captured images.

[0158] In this way, the axle counting device 130 can count the number of axles of ground-contact tires without acquiring distance images from an external device. Therefore, the axle counting system 100 does not need to be equipped with a distance image sensor such as a TOF camera. This allows the configuration of the axle counting system 100 to be simplified. Furthermore, the cost of the axle counting system 100 can be reduced.

[0159] (Other embodiments) The axle count counting device, axle count counting system, and axle count counting method according to one or more aspects of the present disclosure have been described above based on the first embodiment, a modified example of the first embodiment, and the second embodiment (hereinafter also referred to as the embodiments, etc.), but the present disclosure is not limited to these embodiments, etc. As long as they do not deviate from the spirit of the present disclosure, various modifications that a person skilled in the art can make to the embodiments, etc., and forms constructed by combining components of different embodiments may also be included within the scope of one or more aspects of the present disclosure.

[0160] For example, in the above embodiment and the like, an example has been described in which the axle number counting system includes two imaging devices, but the system may include three or more imaging devices.

[0161] In addition, in the above embodiments, an example has been described in which a process is performed to measure the number of axles of rear tires that come into contact with the road, but if two or more front tires are detected, a process is performed to measure the number of axles of rear tires that come into contact with the road, as with the rear tires.

[0162] In the above-described embodiments, the acquiring unit is a communication unit, but the present invention is not limited to this. The acquiring unit may be, for example, a connection unit to which a recording medium is connected. The connection unit may be, for example, a USB terminal to which a USB (Universal Serial Bus) is connected, an SD card slot to which an SD card is inserted, an optical drive to which an optical disc is inserted, or the like.

[0163] The order in which the steps in the flowchart are executed is merely an example for specifically explaining the present disclosure, and other orders may be used. Some of the steps may be executed simultaneously (in parallel) with other steps.

[0164] The division of functional blocks in the block diagram is an example, and multiple functional blocks may be realized as a single functional block, one functional block may be divided into multiple blocks, or some functions may be moved to another functional block.Furthermore, the functions of multiple functional blocks having similar functions may be processed in parallel or in time-sharing by a single piece of hardware or software.

[0165] Furthermore, in the above-described embodiment, the axle counting device is realized by a single device, but it may also be realized by a plurality of devices connected to each other.

[0166] Furthermore, in the above-described embodiments and the like, an example has been described in which the axle count counting device does not include the first imaging device and the second imaging device, i.e., the axle counting device is separate from the first imaging device and the second imaging device. However, the axle count counting device may include at least one of the first imaging device and the second imaging device. For example, the axle count counting device may include both the first imaging device and the second imaging device. In this case, the first imaging device functions as a first imaging unit that is part of the axle count counting device, and the second imaging device functions as a second imaging device that is part of the axle count counting device. In this way, the axle counting system may be configured by a single device (for example, an axle counting device having a first imaging unit and a second imaging unit).

[0167] Furthermore, the communication method between the devices included in the axle counting system in the above-described embodiment is not particularly limited. The devices may communicate wirelessly or via wired lines. Furthermore, the devices may communicate via wireless and wired lines in combination.

[0168] Furthermore, some or all of the components of the axle counting device in the above-described embodiments may be configured as a single system LSI (Large Scale Integration). For example, the axle counting device may be configured as a system LSI having a detection unit, a measurement unit, a determination unit, and a generation unit.

[0169] A system LSI is an ultra-multifunctional LSI manufactured by integrating multiple processing units on a single chip, and is specifically a computer system consisting of a microprocessor, ROM (Read Only Memory), RAM (Random Access Memory), etc. Computer programs are stored in the ROM. The system LSI achieves its functions when the microprocessor operates in accordance with the computer program.

[0170] Although we refer to it as a system LSI here, it may also be called an IC, LSI, super LSI, or ultra LSI depending on the level of integration. Furthermore, the method of integration is not limited to LSI; it can also be realized using dedicated circuits or general-purpose processors. It is also possible to use FPGAs (Field Programmable Gate Arrays), which can be programmed after the LSI is manufactured, or reconfigurable processors, which allow the connections and settings of the circuit cells inside the LSI to be reconfigured.

[0171] Furthermore, if an integrated circuit technology that can replace LSI emerges due to advances in semiconductor technology or other derivative technologies, it is natural that such technology can be used to integrate functional blocks. The application of biotechnology, etc. is also a possibility.

[0172] Furthermore, all or part of the various processes described above may be realized by hardware such as electronic circuits, or by software. Software processes are realized by a processor included in the axle counting device executing a program stored in memory.

[0173] Another aspect of the present disclosure may be a computer program that causes a computer to execute each of the characteristic steps included in the axle counting method. Another aspect of the present disclosure may be a computer-readable non-transitory recording medium on which such a program is recorded. For example, such a program may be recorded on a recording medium and distributed or circulated. For example, the distributed program may be installed in a device having another processor, and the program may be executed by the processor, thereby causing the device to perform each of the above processes. [Industrial Applicability]

[0174] The present disclosure is widely applicable to axle number measurement devices that measure the number of axles of tires in contact with the ground on a vehicle. [Explanation of symbols]

[0175] 1, 1a, 100 Axle Counting System 10 First imaging device 20, 120 Second imaging device 30, 30a, 130 Axle counting device 31 First communication unit (first acquisition unit) 32 Second communication unit (second acquisition unit) 33 Detection unit 34 Measurement section 35 Judgment section 40 vehicles 41, 42 Rear tires 43 Front tire 50 road 136 Generation part (second acquisition part) d1 Amount of change d2 Depression amount J optical axis P1 Captured image (first captured image) P2 Range Image R1, R2 tire area R3, R4 measurement area θ angle

Claims

1. An axle number measuring device for measuring the number of axles of a vehicle traveling on a road, a first acquisition unit that acquires a first captured image including a tire of the vehicle; a detection unit that detects the tire from the first captured image; a second acquisition unit that acquires a plurality of pieces of distance information measured by the distance information measurement device to the road on which the vehicle is traveling; a measurement unit that measures the number of axles supporting the tires that are in contact with the road based on the first captured image and the plurality of pieces of distance information, The measurement unit identifies, from the plurality of pieces of distance information based on the detection result of the tire detected by the detection unit, a first distance from the distance information measurement device to the tire and a plurality of second distances from the distance information measurement device to the underside of the tire, the second distances increasing as the measurement point approaches the tire from the outside of the tire, and when the maximum value of the second distances is greater than a predetermined amount with respect to the first distance, it is determined that the tire is not in contact with the road. Axle counting device.

2. The measurement unit determines that the tire is not in contact with the road if, at the time of change from the first distance to the second distance, the second distance is greater than the first distance by the predetermined amount.

2. The axle counting device according to claim 1.

3. The plurality of distance information are included in a distance image measured by a TOF (Time Of Flight) method.

3. An axle counting device according to claim 1 or 2.

4. The second acquisition unit acquires a second captured image including the tire, the second captured image being captured from a viewpoint different from that of the first captured image, and generates the plurality of pieces of distance information based on the first captured image and the second captured image.

3. An axle counting device according to claim 1 or 2.

5. An axle number measuring device for measuring the number of axles of a vehicle traveling on a road, a first acquisition unit that acquires a first captured image including a tire of the vehicle; a detection unit that detects the tire from the first captured image; a second acquisition unit that acquires a plurality of pieces of distance information measured by the distance information measurement device to the road on which the vehicle is traveling; a determination unit that determines whether the first captured image is an image captured in an environment with a brightness equal to or greater than a predetermined value; a measuring unit that measures the number of axles based on the determination result of the determining unit, The measurement unit (i) determines whether the tire is in contact with the road from the first captured image when the determination unit determines that the first captured image is an image captured in an environment with brightness equal to or higher than a predetermined value, and counts the number of axles based on the determination result; and (ii) determines, when the determination unit determines that the first captured image is not an image captured in an environment with brightness equal to or higher than the predetermined value, a first distance from the distance information measuring device to the tire and a plurality of second distances from the distance information measuring device to an underside of the tire from among the plurality of pieces of distance information based on the tire detection result detected by the detection unit, the second distances increase as the measurement point approaches the tire from the outside of the tire, and determines that the tire is not in contact with the road when the maximum value of the second distances is greater than a predetermined amount with respect to the first distance. Axle counting device.

6. The detection unit further detects a wheel inside the tire from the first captured image, The measurement unit specifies a third distance from the distance information measuring device to the wheel from the plurality of pieces of distance information based on the detection result of the wheel detected by the detection unit, and sets the difference between the first distance and the third distance as the predetermined amount. The axle counting device according to any one of claims 1 to 5.

7. The axle number counting device according to any one of claims 1 to 6, a first imaging device that captures the first captured image; the distance information measuring device that generates the plurality of pieces of distance information; Axle counting system.

8. An axle number counting method for counting the number of axles of a vehicle traveling on a road, comprising: a first acquisition step of acquiring a captured image including a tire of the vehicle; a detection step of detecting the tire from the captured image; a second acquisition step of acquiring a plurality of pieces of distance information measured by a distance information measurement device from the distance information measurement device to the road on which the vehicle is traveling; a measuring step of measuring the number of axles supporting the tires in contact with the road based on the captured image and the plurality of pieces of distance information, The measuring step identifies a first distance from the distance information measuring device to the tire and a plurality of second distances from the distance information measuring device to the underside of the tire from the plurality of pieces of distance information based on the detection result of the detected tire, the second distances increasing as the measurement point approaches the tire from the outside of the tire, and when the maximum value of the second distances is greater than a predetermined amount with respect to the first distance, it is determined that the tire is not in contact with the road. Axle counting method.

9. The detecting step further includes detecting a wheel inside the tire from the captured image, In the measuring step, a third distance from the distance information measuring device to the wheel is identified from the plurality of pieces of distance information based on the detection result of the wheel detected in the detecting step, and a difference between the first distance and the third distance is set as the predetermined amount.

9. The method for counting the number of axles according to claim 8.

Images