JP7111555B2 - TOWING DETERMINATION SYSTEM, VEHICLE CLASSIFICATION SYSTEM, TOWING DETERMINATION METHOD, VEHICLE CLASSIFICATION METHOD, AND PROGRAM - Google Patents

Description

The present invention relates to a traction determination system, a vehicle classification determination system, a traction determination method, a vehicle classification determination method, and a program.

In Patent Document 1, front license plate information is extracted from an entering image, rear license plate information is extracted from an exiting image, and based on these information, it is determined whether or not a vehicle passing through a lane is an illegal vehicle. A technique for doing so is disclosed.

JP 2016-095733 A

By the way, the above document describes detecting the shape of the vehicle with an optical sensor and determining whether or not the vehicle passing through the lane is towing the vehicle to be towed.

However, with the method of detecting the shape of the vehicle using an optical sensor, it is difficult to accurately determine whether or not the vehicle is towing the towed vehicle. For example, in the case of a full trailer, there are no regulations regarding the size of the tow bar that connects the towing vehicle and the vehicle to be towed, and errors in detection of the tow bar are likely to occur. In addition, the semi-trailer cannot be distinguished in the first place because its outer shape when connected is the same as that of a normal truck.

The present invention has been made in view of the above problems, and its main purpose is to provide a towing determination system and a vehicle classification determination system capable of accurately determining whether or not a vehicle is towing a towed vehicle. , a traction determination method, a vehicle classification determination method, and a program.

In order to solve the above problems, a towing determination system according to one aspect of the present invention provides a first camera installed at a position including a license plate attached to the rear of a vehicle in an imaging range, and a plate detection unit that detects the license plate included in the image obtained; and a towing determination unit that determines that the vehicle is towing the towed vehicle when the number of the detected license plates is two or more. , provided.

In another aspect of the traction determination system of the present invention, a first camera is installed in a position including a license plate attached to the rear of the vehicle in an imaging range, and an image generated by the first camera includes a plate detection unit for detecting the license plate; a passage detection unit for detecting passage of the rear end of the vehicle; timing at which the first license plate is detected; timing at which the rear end of the vehicle is detected to pass; and a towing determination unit that determines whether the vehicle is towing the towed vehicle based on the relationship between the towed vehicle and the towed vehicle.

According to another aspect of the present invention, there is provided a vehicle classification determination system comprising any one of the towing determination systems described above, a classification information acquisition unit that acquires a vehicle classification of the vehicle, and a vehicle that is towing a towed vehicle. and a class determination unit that upgrades and classifies a vehicle class of the vehicle when determined.

Further, a traction determination method according to another aspect of the present invention includes generating an image by a first camera installed at a position including a photographing range of a license plate attached to the rear of the vehicle, and obtaining the license plate included in the image. is detected, and when the number of the detected license plates is two or more, it is determined that the vehicle is towing the towed vehicle.

Further, a traction determination method according to another aspect of the present invention includes generating an image by a first camera installed at a position including a photographing range of a license plate attached to the rear of the vehicle, and obtaining the license plate included in the image. is detected, and the passage of the rear end of the vehicle is detected, and based on the relationship between the timing at which the first license plate is detected and the timing at which the passage of the rear end of the vehicle is detected, Determine whether the towing vehicle is being towed.

A vehicle classification determination method according to another aspect of the present invention determines whether or not the vehicle is towing a towed vehicle by any of the towing determination methods described above, acquires the vehicle classification of the vehicle, If it is determined that the vehicle is towing a towed vehicle, the vehicle classification of the vehicle is upgraded to determine the classification.

In another aspect of the present invention, there is provided a program for detecting a license plate included in an image generated by a first camera installed at a position including a photographing range of a license plate attached to the rear of a vehicle. and a towing determination unit that determines that the vehicle is towing the towed vehicle when the number of the detected license plates is two or more.

In another aspect of the present invention, there is provided a program for detecting a license plate included in an image generated by a first camera installed at a position including a photographing range of a license plate attached to the rear of a vehicle. a passage detection unit that detects passage of the rear end of the vehicle; and a relationship between the timing at which the first license plate is detected and the timing at which the rear end of the vehicle is detected. The computer is caused to function as a traction determination unit that determines whether or not the vehicle is towing the towed vehicle.

According to the present invention, it is possible to accurately determine whether or not the vehicle is towing the vehicle to be towed.

It is a figure which shows the structural example of the traction determination system which concerns on embodiment. It is a block diagram showing an example of the functional configuration of the traction determination system. FIG. 4 is a diagram showing an example of a case where a vehicle that is not towing a vehicle to be towed passes. FIG. 4 is a diagram showing an example of a case where a vehicle that is towing a vehicle to be towed passes; FIG. 4 is a flow diagram showing an example of the procedure of a towing determination method according to the embodiment; FIG. 7 is a flow chart showing another procedure example of the towing determination method according to the embodiment; 1 is a block diagram showing a functional configuration example of a vehicle classification determination system according to an embodiment; FIG. FIG. 3 is a flow diagram showing an example procedure of a vehicle classification determination method according to the embodiment; It is a figure for demonstrating a vehicle classification.

Preferred embodiments of the present invention will be described below with reference to the drawings. It should be noted that each of the embodiments shown below exemplifies a method and apparatus for embodying the technical idea of the present invention, and the technical idea of the present invention is not limited to the following. do not have. Various modifications can be made to the technical idea of the present invention within the technical scope described in the claims.

[Towing judgment system]
FIG. 1 is a diagram showing a configuration example of a traction determination system 1 according to an embodiment. FIG. 2 is a block diagram showing a functional configuration example of the traction determination system 1. As shown in FIG. The traction determination system 1 is a system for determining whether or not a vehicle T passing through a lane L is towing a towed vehicle TL. A lane L is a toll collection lane provided at an entrance or the like of a toll road, a parking lot, or the like, for example.

An arrow I in the drawing indicates the entrance side of the lane L (rear direction for the vehicle T), and an arrow O indicates the exit side of the lane L (forward direction for the vehicle T).

In the example shown in FIG. 1, the vehicle T includes a towing vehicle TC and a towed vehicle TL coupled to the towing vehicle TC. For example, the towing vehicle TC is a semi-tractor and the towed vehicle TL is a semi-trailer. Alternatively, the towing vehicle TC may be a full tractor and the towed vehicle TL may be a full trailer.

At least three license plates are attached to the vehicle T that tows the towed vehicle TL. Specifically, a forward-facing license plate N1 attached to the front end of the towing vehicle TC, a rear-facing license plate N2 attached to the rear end of the towing vehicle TC, and a rear-facing license plate N2 attached to the towed vehicle TL's rear end. There is a license plate N3 attached to.

The towing determination system 1 includes a front camera 31 (example of a second camera), a rear camera 32 (example of a first camera), a vehicle detection sensor 4 and an axle detection sensor 5 installed in the lane L.

The front camera 31 is installed at a position (for example, see FIG. 1, etc.) including the front-facing license plate N1 of the vehicle T passing through the lane L in its imaging range. The front camera 31 is installed closer to the exit side (rear side) of the lane L than the rear camera 32, and photographs toward the entrance side of the lane L.

The rear-side camera 32 is installed at a position (for example, see FIG. 1, etc.) that includes the rear-facing license plates N2 and N3 of the vehicle T passing through the lane L in its photographing range. The rear camera 32 is installed closer to the entrance side (front side) of the lane L than the front camera 31, and photographs toward the exit side of the lane L.

Since the towed vehicle TL is positioned above the rear end portion of the towing vehicle TC, it is difficult to photograph the license plate N2 attached to the rear end portion of the towing vehicle TC from above. Therefore, the rear camera 32 is preferably installed at a position (for example, on the side of the lane L or on the ground) where the license plate N2 attached to the rear end of the towing vehicle TC can be photographed.

For example, when the rear camera 32 is installed on the side of the lane L, it is preferable that the photographing direction of the rear camera 32 faces the horizontal direction or above. Also, since the license plate N2 may be attached to the left side or the right side of the rear end of the towing vehicle TC, the rear camera 32 may be installed on both the left and right sides of the lane L.

The vehicle detection sensor 4 is a sensor for detecting a vehicle T passing through the lane L. The vehicle detection sensor 4 includes a light projecting section 41 and a light receiving section 42 which are installed on the left and right sides of the lane L apart from each other. When the vehicle T blocks the light beam from the light projecting unit 41 toward the light receiving unit 42 and the light receiving unit 42 stops receiving the light beam, the entry of the vehicle T is detected. After that, when the light receiving unit 42 receives the light again, the leaving of the vehicle T is detected. The vehicle T may be detected using not only light but also radio waves, sound waves, or the like.

The axle detection sensor 5 is a sensor that detects the axle of the vehicle T passing through the lane L. As shown in FIG. The axle detection sensor 5 is a tread-type sensor embedded in the lane L, and detects a load applied from the wheels of the vehicle T. As shown in FIG. The axle detection sensor 5 includes, for example, a hollow member made of an elastic material and a fluid pressure sensor that measures the pressure of liquid filled in the hollow member. Alternatively, the wheels may be detected using a light beam or the like, or the wheels may be detected by analyzing an image captured by a camera.

In the example shown in FIG. 1, two sets of the vehicle detection sensor 4 and the axle detection sensor 5 are installed apart from each other in the longitudinal direction of the lane L, but the present invention is not limited to this, and only one set may be installed. , three or more sets may be installed. Further, the vehicle detection sensor 4 and the axle detection sensor 5 may be installed at positions different from each other in the longitudinal direction of the lane L.

Moreover, the positional relationship among the cameras 31 and 32, the vehicle detection sensor 4, and the axle detection sensor 5 is not limited to the example shown in FIG. For example, the front camera 31 may be positioned closer to the entrance than the vehicle detection sensor 4 and the axle detection sensor 5 on the exit side, or the rear camera 32 may be positioned closer to the exit than the vehicle detection sensor 4 and the axle detection sensor 5 on the entrance side. can be located on the side.

As shown in FIG. 2, image data generated by the cameras 31 and 32, detection signals from the vehicle detection sensor 4, and the like are output to the control device 10. FIG.

The control device 10 is a computer including a CPU, RAM, ROM, nonvolatile memory, an input/output interface, and the like. The control device 10 includes a plate detection section 11 , a passage detection section 12 and a traction determination section 13 . These functional units are realized by the CPU executing information processing according to programs loaded from the ROM or nonvolatile memory to the RAM.

The program may be supplied via an information storage medium such as an optical disk or memory card, or may be supplied via a communication network such as the Internet.

The control device 10 may be installed in the vicinity of the lane L and directly connected to the cameras 31 and 32, the vehicle detection sensor 4, etc., or may be installed in a remote location such as a data center, and may receive image data and the like via a communication network. A detection signal or the like may be acquired. Also, some functions of the control device 10 may be realized by another device capable of communicating with the control device 10 .

The plate detector 11 detects license plates included in the images generated by the cameras 31 and 32 . The front-facing license plate N1 of the vehicle T is detected from the image generated by the front-side camera 31, and the rear-facing license plates N2 and N3 of the vehicle T are detected from the image generated by the rear-side camera 32.

Specifically, the plate detection unit 11 performs image processing such as edge detection and binarization on the images generated by the cameras 31 and 32, and extracts a rectangular area to detect the license plate.

The cameras 31 and 32 output a plurality of time-series images, and the plate detection unit 11 detects a license plate included in each of the plurality of time-series images. The plurality of time-series images may be, for example, a plurality of still images included in moving image data, or may be a plurality of still images captured at predetermined time intervals and individually generated.

The plate detection unit 11 does not have to perform character recognition of the license plate. As a result, the processing load can be reduced and the processing time can be shortened, and the problem of erroneous recognition does not occur. Note that this description does not exclude character recognition of the license plate.

The passage detector 12 detects a vehicle T passing through the lane L based on the detection signal from the vehicle detection sensor 4 . Specifically, the passage detection unit 12 detects the entry of the vehicle T into the lane L when the detection signal from the vehicle detection sensor 4 changes from the non-detection state to the detection state, and changes from the detection state to the non-detection state. The exit of the vehicle T from the lane L is detected when it changes.

In the case where there are a plurality of vehicle detection sensors 4 as in the example shown in FIG. The exit of the vehicle T from the lane L may be detected by a detection signal from the vehicle detection sensor 4 on the side.

The towing determination unit 13 determines whether or not the vehicle T is towing the towed vehicle TL based on the outputs from the plate detection unit 11 and the passage detection unit 12 .

In the first example, the towing determination unit 13 determines that the towed vehicle TL is towed by the vehicle T when the number of rearward-facing license plates detected from the image generated by the rear camera 32 is two or more. When the number of rearward license plates is 1, it is determined that the vehicle T is not towing the towed vehicle TL.

As shown in FIG. 3, when a vehicle T not towing a towed vehicle TL passes through lane L, one forward-facing license plate N1 is detected from the image generated by front camera 31 and rear camera 32 One rear-facing license plate N2 is also detected from the image generated by .

On the other hand, as shown in FIG. 4, when the vehicle T towing the towed vehicle TL passes through the lane L, the front-facing license plate N1 of the towing vehicle TC is detected from the image generated by the front camera 31. , the rear-facing license plate N2 of the towing vehicle TC, which is the same as the front-facing license plate N1, is detected from the image generated by the rear camera 32, and the rear-facing license plate 3 of the towed vehicle TL is also detected.

For example, in a plurality of time-series images generated by the rear camera 32, the rear-facing license plate N2 of the towing vehicle TC and the rear-facing license plate N3 of the towed vehicle TL appear in order.

The towing determination unit 13 counts the number of rearward-facing license plates N2 and N3 that appear in order in a plurality of time-series images in this way, and when the number of rearward-facing license plates is two or more, the vehicle T is hit. It is determined that the tractor TL is towed. On the other hand, the towing determination unit 13 determines that the vehicle T is towing the towed vehicle TL when the exit of the vehicle T is detected by the detection signal from the vehicle detection sensor 4 while the number of rearward license plates remains 1. judge not.

In the second example, the towing determination unit 13 detects the rear end of the vehicle T based on the timing when the first rearward-facing license plate N2 is detected from the image of the rear camera 32 and the detection signal from the vehicle detection sensor 4. is detected, it is determined whether or not the vehicle T is towing the towed vehicle TL.

As shown in FIG. 3, when a vehicle T that does not tow a towed vehicle TL passes through the lane L, the license plate N2 facing backward is attached to the rear end of the vehicle T. The time difference between the timing at which the rear-facing license plate N2 is detected from the image and the timing at which the detection signal from the vehicle detection sensor 4 detects the passing of the rear end of the vehicle T is relatively small.

On the other hand, as shown in FIG. 4, when the vehicle T towing the towed vehicle TL passes through the lane L, the first rearward facing license plate N2 is attached to the rear end of the towing vehicle TC. Since it is separated from the rear end of the vehicle T (that is, the rear end of the towed vehicle TL), the timing at which the first rearward license plate N2 is detected from the image of the rear camera 32 and the vehicle detection sensor The time difference from the timing at which the passage of the rear end of the vehicle T is detected by the detection signal from 4 becomes relatively large.

Therefore, the towing determination unit 13 determines the timing at which the first rearward-facing license plate N2 is detected from the image of the rear camera 32 and the timing at which the passage of the rear end of the vehicle T is detected by the detection signal from the vehicle detection sensor 4. If the time difference is equal to or greater than the threshold, it is determined that the vehicle T is towing the towed vehicle TL, and if the time difference is less than the threshold, the vehicle T is the towed vehicle TL is not towed.

When there are a plurality of vehicle detection sensors 4 , any vehicle detection sensor 4 may detect the passage of the rear end of the vehicle T. For example, the vehicle detection sensor 4 on the entrance side of the lane L may be used for detection, or the vehicle detection sensor 4 on the exit side of the lane L may be used for detection.

FIG. 5 is a flowchart showing a procedure example of the traction determination method according to the embodiment, which is realized by the control device 10 of the traction determination system 1. As shown in FIG. The traction determination shown in the figure corresponds to the first example described above.

When the control device 10 detects that the vehicle T has entered the lane L based on the detection signal from the vehicle detection sensor 4 (S11), it starts towing determination (S12).

When the towing determination is started, the control device 10 first detects the front-facing license plate N1 from the image of the front camera 31 (S13), and then detects the first rear-facing license plate N2 from the image of the rear camera 32 (S13). S14).

Then, the control device 10 determines whether or not the second rearward-facing license plate N3 is detected from the image of the rear camera 32 (S15, first example of processing by the towing determination unit 13).

When the second rearward-facing license plate N3 is detected (S15: YES), and the exit of the vehicle T is detected by the detection signal from the vehicle detection sensor 4 (S16), the control device 10 detects that the vehicle T is the towed vehicle. It is determined that the TL is being towed (S17), and the towing determination is ended (S20).

On the other hand, when the exit of the vehicle T is detected by the detection signal from the vehicle detection sensor 4 without detecting the second rearward-facing license plate N3 (S15: NO) (S18), the control device 10 detects that the vehicle T It is determined that the towed vehicle TL is not towed (S19), and the towing determination is terminated (S20).

If the positional relationship between the rear camera 32 on the entrance side and the vehicle detection sensor 4 on the entrance side shown in FIG. The timing at which the second rearward license plate N3 is detected and the timing at which the exit of the vehicle T is detected are switched.

FIG. 6 is a flowchart showing another procedure example of the traction determination method according to the embodiment, which is implemented by the control device 10 of the traction determination system 1. As shown in FIG. The traction determination shown in the figure corresponds to the second example described above. Steps that overlap with those in the flow chart of FIG. 5 are given the same numbers, and detailed description thereof will be omitted.

When the control device 10 detects the first rearward-facing license plate N2 from the image of the rear camera 32 (S14), it counts (S21) until the exit of the vehicle T is detected by the detection signal from the vehicle detection sensor 4. is equal to or greater than the threshold value (S22, second example of processing by the traction determination unit 13).

If the time from detection of the first rearward license plate N2 to detection of exit of the vehicle T is equal to or greater than the threshold value (S22: YES), the control device 10 determines that the vehicle T tows the towed vehicle TL. It is determined that the vehicle is present (S17), and the towing determination is terminated (S20).

On the other hand, if the time from detection of the first rearward license plate N2 to detection of exit of the vehicle T is less than the threshold (S22: NO), the control device 10 determines that the vehicle T tows the towed vehicle TL. It is determined that it is not (S19), and the towing determination is terminated (S20).

Considering the case where the positional relationship between the rear camera 32 on the entrance side and the vehicle detection sensor 4 on the entrance side shown in FIG. , if the vehicle T is not towing the towed vehicle TL, the first rearward license plate N2 is detected after the exit of the vehicle T is detected, but if the vehicle T is towing the towed vehicle TL. Since these timings can be reversed, the presence or absence of towing may be determined depending on which is detected first.

Also, the time from detection of the first rearward-facing license plate N2 to detection of exit of the vehicle T may vary depending on the vehicle speed of the vehicle T passing through the lane L. Therefore, a speed measuring device may be provided to detect the vehicle speed of the vehicle T passing through the lane L, and the threshold value may be changed according to the detected vehicle speed. Specifically, the threshold is relatively increased when the vehicle speed is relatively high, and the threshold is relatively increased when the vehicle speed is relatively low. The velocity measuring device may be, for example, of radar type or may be based on image analysis.

[Vehicle Classification System]
FIG. 7 is a block diagram showing a functional configuration example of the vehicle classification determination system 100 according to the embodiment. The vehicle classification determination system 100 is a system for determining the vehicle classification of the vehicle T passing through the lane L and the toll classification. , and has the function of adjusting the vehicle classification according to the result.

The vehicle classification determination system 100 includes a configuration that overlaps with the traction determination system 1 described above. The same numbers are assigned to the same components as those of the towing determination system 1 described above, and detailed description thereof will be omitted.

In addition to the plate detection unit 11, the passage detection unit 12, and the traction determination unit 13, the control device 10 of the vehicle classification determination system 100 includes the classification information acquisition unit 14, the axle number detection unit 15, the classification determination unit 16, and the toll identification unit 17. I have. These functional units are also implemented by the CPU executing information processing according to programs loaded from the ROM or nonvolatile memory to the RAM.

The classification information acquisition unit 14 acquires the vehicle classification of the vehicle T passing through the lane L. FIG. Vehicle categories include, for example, light vehicles, ordinary vehicles, medium-sized vehicles, large vehicles, and extra-large vehicles. If the vehicle T is towing the towed vehicle TL, the vehicle class of the towing vehicle TC is acquired. The classification information acquisition unit 14 may acquire the vehicle classification from an ETC on-board device (not shown) mounted on the vehicle T using an ETC roadside device (not shown) provided in the lane L, for example. The vehicle classification may be determined by recognizing the characters and colors of the front-facing license plate N1 of the vehicle T included in the image from the camera 31 (see FIG. 1).

The axle number detection unit 15 detects the number of axles of the vehicle T passing through the lane L based on the detection signal from the axle detection sensor 5 . Specifically, the axle number detection unit 15 counts the number of maximum values of the detection signal representing the load from the tread type axle detection sensor 5 as the number of axles.

The classification determination unit 16 acquires the vehicle classification of the vehicle T from the classification information acquisition unit 14, and if the towing determination unit 13 determines that the vehicle T is towing the towed vehicle TL, the classification information acquisition unit 16 14 to upgrade the vehicle classification of the vehicle T to determine the final vehicle classification (classification decision).

That is, since the vehicle classification of the vehicle T changes depending on whether or not the towed vehicle TL is towed, the classification determination unit 16 determines by the traction determination unit 13 that the vehicle T is towing the towed vehicle TL. If so, the vehicle classification of the vehicle T acquired from the classification information acquisition unit 14 (that is, the vehicle classification of the towing vehicle TC) is upgraded to a higher vehicle classification.

Also, the classification determination unit 16 selects the grade number of the vehicle classification to be upgraded based on the number of axles detected by the axle number detection unit 15 . Details of this will be described later.

After acquiring the vehicle class of the vehicle T from the class determination unit 16, the toll identifying unit 17 identifies the toll corresponding to the vehicle class of the vehicle T based on a predetermined relationship between the vehicle class and the toll. Table data describing the relationship between vehicle classifications and tolls is stored in the memory or the like of the control device 10 and referred to by the toll identification unit 17 .

FIG. 8 is a flowchart showing an example procedure of the vehicle classification method according to the embodiment, which is implemented by the control device 10 of the vehicle classification system 100. As shown in FIG. Steps overlapping those in the flow chart of FIG. 4 or FIG. 5 are given the same numbers, and detailed description thereof will be omitted. FIG. 9 is a diagram for explaining vehicle classification.

The controller 10 counts the number of axles detected by the axle detection sensor 5 until the first rearward-facing license plate N2 is detected in S14 (S23). This is a step for detecting the number of axles located ahead of the first rearward-facing license plate N2, that is, the number of axles of the tractor TC.

If the number of axles detected before the first rear-facing license plate N2 is detected is 2 (S23: n=2), it corresponds to a light vehicle, normal vehicle, or medium/large vehicle (2 axles). (See Figure 9). On the other hand, if the number of axles detected before the first rear-facing license plate N2 is detected is 3 or more (S23: n≧3), it corresponds to a medium/large vehicle (3 axles) or an extra-large vehicle (Fig. 9).

Next, when the controller 10 detects the first rearward-facing license plate N2 (S14), whether the time from the detection of the first rearward-facing license plate N2 to the detection of the exit of the vehicle T is equal to or greater than a threshold value. It is determined whether or not (S22).

The number of axles detected before the first rearward license plate N2 is detected is two (S23: n=2), and the departure of the vehicle T is detected after the first rearward license plate N2 is detected. If the time until the vehicle is detected is equal to or greater than the threshold (S22: YES), the control device 10 counts the number of axles detected by the axle detection sensor 5 after the first rearward-facing license plate N2 is detected (S24). This is a step for detecting the number of axles behind the first rear-facing license plate N2, that is, the number of axles of the towed vehicle TL.

When the number of axles of the towed vehicle TL is one, for example, light vehicles (tractor vehicle category) → ordinary vehicles (last vehicle category), ordinary vehicles (towing vehicle category) → medium-sized vehicles (last vehicle category). In addition, the vehicle class needs to be upgraded by one grade (see Figure 9). On the other hand, when the number of axles of the towed vehicle TL is 2 or more, for example, light vehicle (tractor vehicle category) → medium-sized vehicle (last vehicle category), ordinary vehicle (tractor vehicle category) → large vehicle (last vehicle category) In this way, the vehicle classification needs to be upgraded by two grades (see FIG. 9).

Therefore, when the number of axles detected after the first rearward-facing license plate N2 is detected is one (S24: n=1) and the second rearward-facing license plate N3 is detected (S25), The control device 10 determines that the vehicle T is towing the towed vehicle TL (S17, traction determination), upgrades the vehicle class of the vehicle T by one grade (S27, class determination), and determines the upgraded vehicle class. (S30), and the process ends.

On the other hand, when the number of axles detected after the first rearward-facing license plate N2 is detected is 2 or more (S24: n≧2) and the second rearward-facing license plate N3 is detected (S25), The control device 10 determines that the vehicle T is towing the towed vehicle TL (S17, traction determination), upgrades the vehicle class of the vehicle T by two grades (S28, class determination), and determines the upgraded vehicle class. (S30), and the process ends.

The number of axles detected before the first rearward license plate N2 is detected is two (S23: n=2), and the departure of the vehicle T is detected after the first rearward license plate N2 is detected. is less than the threshold (S22: NO) and the second rearward-facing license plate N3 is not detected (S26), the control device 10 determines that the vehicle T is not towing the towed vehicle TL. (S19, towing determination), the toll corresponding to the vehicle class of the vehicle T is specified (S30), and the process ends.

If the number of axles detected before the first rear-facing license plate N2 is detected is 3 or more (S23: n≧3), it corresponds to a medium/large vehicle (3 axles) or an oversized vehicle, but a towing vehicle If the TC is towing a towed vehicle TL, whether it is a medium/large vehicle (three axles) or an oversized vehicle, the final vehicle category will be the highest grade "oversized vehicle" (see FIG. 9).

Therefore, if the number of axles detected before the first rearward-facing license plate N2 is detected is 3 or more (S23: n≧3), the exit of the vehicle T is prohibited after the first rearward-facing license plate N2 is detected. If the time until detection is equal to or greater than the threshold (S22: YES) and the second rearward-facing license plate N3 is detected (S25), the control device 10 detects that the vehicle T is towing the towed vehicle TL. (S17, towing determination), the vehicle classification of vehicle T is set to "extra-large vehicle" (S29, classification determination), the toll corresponding to "extra-large vehicle" is specified (S30), and the process ends.

The number of axles detected before the first rearward license plate N2 is detected is 3 or more (S23: n≧3), and the departure of the vehicle T is detected after the first rearward license plate N2 is detected. is less than the threshold (S22: NO) and the second rearward-facing license plate N3 is not detected (S26), the control device 10 determines that the vehicle T is not towing the towed vehicle TL. (S19, towing determination), the toll corresponding to the vehicle class of the vehicle T is specified (S30), and the process ends.

Note that the timing at which the rear-facing license plate N2 is first detected (S14) may vary depending on the positional relationship between the rear camera 32 and the axle detection sensor 5, the processing time of the image generated by the rear camera 32, and the like. In this case, it is preferable to compensate for the deviation before counting the number of axles (S23, S24).

In the vehicle classification determination method described above, regarding the determination of whether or not the vehicle T is towing the towed vehicle TL, the time from the detection of the first rearward-facing license plate N2 to the detection of the exit of the vehicle T is Although the second example (see FIG. 6) for determining whether is greater than or equal to the threshold is applied, the present invention is not limited to this. The first example (see FIG. 5) may be applied.

The installation mode of the rear camera 32 is not limited to the above example. may recognize a plurality of rear-facing license plates N2, N3.

In addition, a plurality of rear cameras 32 may be installed in order to separately photograph the rear-facing license plate N2 of the towing vehicle TC and the rear-facing license plate N3 of the towed vehicle TL. In addition, since the position of the rear-facing license plate N2 of the towing vehicle TC is likely to be shadowed, the rear camera 32 may be illuminated.

1 traction determination system, 10 control device, 11 plate detection unit, 12 passage detection unit, 13 traction determination unit, 14 classification information acquisition unit, 15 axle number detection unit, 16 classification determination unit, 17 toll identification unit, 31 front camera ( 2nd camera), 32 rear side camera (first camera), 4 vehicle detection sensor, 41 light emitting unit, 42 light receiving unit, 5 axle detection sensor, 100 vehicle classification discrimination system, T vehicle, TC towing vehicle, TL towed car, L lane

Claims (14)

a first camera installed at a position including a vehicle that tows a towed vehicle passing through the lane and each license plate attached to each of the towed vehicles facing rearward, in a shooting range;
a plate detection unit that detects the license plate included in the image generated by the first camera;
a towing determination unit that determines that the vehicle is towing the towed vehicle when the number of the license plates detected when the vehicle passes through the lane is two or more;
A towing determination system. The plate detection unit detects the license plate included in a plurality of time-series images generated by the first camera.
The traction determination system according to claim 1. The traction determination unit counts the number of license plates that appear in order in the plurality of time-series images.
The traction determination system according to claim 2. Further comprising an entry detection unit that detects entry of the vehicle into the lane,
The towing determination unit starts counting the number of license plates from the time when the entry of the vehicle is detected.
The traction determination system according to any one of claims 1 to 3. Further comprising a second camera installed at a position including a license plate attached to the front of the vehicle in a shooting range,
The traction determination system according to any one of claims 1 to 4. further comprising a passage detection unit that detects passage of the rear end of the vehicle;
The towing determination unit determines that the vehicle is towing the towed vehicle when the number of the detected license plates is two or more and the passage of the rear end of the vehicle is detected. ,
The traction determination system according to any one of claims 1 to 5. A traction determination system according to any one of claims 1 to 6 ;
a classification information acquisition unit that acquires a vehicle classification of the vehicle;
a classification determination unit that upgrades and determines a vehicle classification of the vehicle when it is determined that the vehicle is towing the towed vehicle;
A vehicle classification system. Further comprising an axle number detection unit that detects the number of axles of the vehicle,
The classification determination unit determines that the vehicle is towing the towed vehicle, and when the number of axles detected after the timing at which the first license plate is detected is 1, The vehicle classification is upgraded by one grade, or the number of axles detected after the timing when it is determined that the vehicle is towing the towed vehicle and the first license plate is detected is 2 or more. upgrade the vehicle class of the vehicle by two grades,
The vehicle class discrimination system according to claim 7 . Further comprising an axle number detection unit that detects the number of axles of the vehicle,
When it is determined that the vehicle is towing the towed vehicle and the number of axles detected before the timing at which the first license plate is detected is 3 or more, the classification determination unit determines the Upgrade a vehicle's vehicle class to the highest grade,
9. The vehicle class discrimination system according to claim 7 or 8 . further comprising a charge identification unit that identifies a charge corresponding to the vehicle class of the vehicle based on a predetermined relationship between the vehicle class and the charge;
10. The vehicle class discrimination system according to any one of claims 7 to 9 . An image is generated by a first camera installed at a position including a vehicle that tows a towed vehicle passing through the lane and each license plate attached to each of the towed vehicles facing backward, and
A plate detection unit detects the license plate included in the image,
determining that the vehicle is towing the towed vehicle when the number of the license plates detected when the vehicle passes through the lane is two or more by the towing determination unit ;
Traction judgment method. determining whether the vehicle is towing the towed vehicle by the towing determination method according to claim 11 ;
Acquiring the vehicle classification of the vehicle by the classification information acquisition unit ,
When the classification determination unit determines that the vehicle is towing the towed vehicle, the classification is determined by upgrading the vehicle classification of the vehicle.
Vehicle classification method. The license plate included in the image generated by the first camera installed at a position that covers the vehicle that tows the towed vehicle passing through the lane and the license plate attached to each of the towed vehicles facing rearward. A plate detection unit that detects the
a traction determination unit that determines that the vehicle is towing the towed vehicle when the number of the license plates detected when the vehicle passes through the lane is two or more;
A program that makes a computer function as a moreover,
a classification information acquisition unit that acquires a vehicle classification of the vehicle; and
a classification determining unit that upgrades and determines a vehicle classification of the vehicle when it is determined that the vehicle is towing the towed vehicle;
14. The program according to claim 13 , which causes a computer to function as

Images