JP7296898B2 - AXLE NUMBER DETECTION DEVICE, TOLL COLLECTION SYSTEM, AXLE NUMBER DETECTION METHOD, AND PROGRAM - Google Patents

Description

The present disclosure relates to an axle number detection device, a toll collection system, an axle number detection method, and a program.

In a toll collection system for a toll road, a method of determining a toll based on the type of vehicle is known as a method of determining tolls. The vehicle type is determined using various vehicle information such as the number of axles, vehicle length, vehicle height, license plate information, and whether or not the vehicle is towed.
For example, Patent Literature 1 discloses a method of determining the number of axles of a running vehicle as vehicle information.

WO2019/064682

Some vehicles have a lift axle function that automatically switches between grounding and non-grounding of specific axles (tires) depending on whether the load weight exceeds a certain value. For such vehicles, the type of vehicle (that is, the toll) is determined based on the number of axles that are grounded.
However, it is assumed that the number and positions of axles that can be switched between grounded and non-grounded are different for each vehicle having a lift axle function. Therefore, when an axle that is not assumed in the toll collection system is lifted up, there is a concern that the number of axles of the vehicle cannot be detected correctly.

An object of the present disclosure is to provide an axle number detection device, a toll collection system, an axle number detection method, and a program that make it difficult to erroneously detect the number of axles of grounded tires.

According to one aspect of the present disclosure, an axle number detection device includes an image acquisition unit that acquires a side image of a vehicle, an area identification unit that identifies a front area and a rear area of the vehicle in the side image, and the front area. A reference line is generated on the side image based on the position on the side image of the tire belonging to the rear region and the position on the side image of the tire drawn at the lowest position among the tires belonging to the rear region. and a lift-up axis determination unit that determines a tire that is away from the reference line by a predetermined value or more as a lift-up axis.

According to one aspect of the present disclosure, an axle number detection device includes an image acquisition unit that acquires a side image of a vehicle, and a height acquisition unit that acquires the height of each tire included in the side image on the side image. a low-position tire identifying unit that identifies the two lowest tires among a plurality of tires whose heights are acquired; and a reference line that connects the reference points of the two lowest tires, and and a lift-up axis determination unit that determines a tire that is separated by a predetermined value or more as a lift-up axis.

According to one aspect of the present disclosure, an axle number detection device includes: an image acquisition unit that acquires a side image of a vehicle; an acquisition unit, and a distribution identification that creates a histogram showing the number of tires in each height section in the side image, and identifies a first group in the histogram and a second group that is a section higher than the first group. and a lift-up axis determination unit that determines a tire belonging to the second group among the plurality of tires included in the side image as a lift-up axis.

According to one aspect of the present disclosure, a toll collection system includes the axle number detection device described above; Prepare.

According to one aspect of the present disclosure, a method for detecting the number of axles includes the steps of acquiring a side image of a vehicle, identifying a front area and a rear area of the vehicle in the side image, and determining the number of tires belonging to the front area. A reference line is generated on the side image based on the position on the side image and the position on the side image of the tire drawn at the lowest position among the tires belonging to the rear region, and the reference line is generated on the side image. and determining a tire separated from the line by a predetermined value or more as a lift-up axis.

According to one aspect of the present disclosure, a program causes a computer of an axle number detection device to acquire a side image of a vehicle; identify a front region and a rear region of the vehicle in the side image; A reference line is drawn on the side image based on the position on the side image of the tire belonging to the area and the position on the side image of the tire drawn at the lowest position among the tires belonging to the rear area. and determining a tire that is separated from the reference line by a predetermined value or more as a lift-up axis.

According to the axle number detection device, the toll collection system, the axle number detection method, and the program according to each aspect described above, it is possible to make it difficult to detect the number of axles of the grounded tires by mistake.

BRIEF DESCRIPTION OF THE DRAWINGS It is a figure which shows the whole structure of the toll collection system which concerns on 1st Embodiment. It is a figure which shows the functional structure of the toll collection system which concerns on 1st Embodiment. It is a figure which shows the processing flow of the toll collection system which concerns on 1st Embodiment. FIG. 4 is an explanatory diagram showing details of processing of the toll collection system according to the first embodiment; FIG. 4 is an explanatory diagram showing details of processing of the toll collection system according to the first embodiment; FIG. 4 is an explanatory diagram showing details of processing of the toll collection system according to the first embodiment; FIG. 4 is an explanatory diagram showing details of processing of the toll collection system according to the first embodiment; It is explanatory drawing which shows the content of the process of the toll collection system based on the 1st modification of 1st Embodiment. FIG. 11 is an explanatory diagram showing details of processing of the toll collection system according to the second modification of the first embodiment; FIG. 11 is an explanatory diagram showing details of processing of the toll collection system according to the second modification of the first embodiment; It is a figure which shows the function structure of the toll collection system which concerns on 2nd Embodiment. It is a figure which shows the processing flow of the toll collection system which concerns on 2nd Embodiment. It is an explanatory view showing the contents of the processing of the toll collection system according to the second embodiment. It is a figure which shows the function structure of the toll collection system which concerns on 3rd Embodiment. It is a figure which shows the processing flow of the toll collection system which concerns on 3rd Embodiment. It is explanatory drawing which shows the content of the process of the toll collection system which concerns on 3rd Embodiment. It is explanatory drawing which shows the content of the process of the toll collection system which concerns on 3rd Embodiment.

<First embodiment>
Hereinafter, the toll collection system according to the first embodiment and its modification will be described in detail with reference to FIGS. 1 to 10. FIG.

(Configuration of toll collection system)
FIG. 1 is a diagram showing the overall structure of a toll collection system according to the first embodiment.
FIG. 2 is a diagram showing the functional configuration of the toll collection system according to the first embodiment.
Hereinafter, the configuration of the toll collection system 1 according to the first embodiment will be described in detail with reference to FIGS. 1 and 2. FIG.

The toll collection system 1 according to the first embodiment is provided, for example, at an entrance toll gate in a uniform toll section (a section in which the excess amount is constant regardless of the travel distance) of a toll road, and a user of the toll road, This is a system for collecting a fee corresponding to the type of vehicle AA that the user rides.
In other embodiments, the toll collection system 1 is not limited to this aspect. For example, the toll collection system 1 is installed at an entrance tollgate or an exit tollgate of a distance-based charging section (a section in which the excess amount changes according to the distance traveled). may be When installed at the entrance tollgate of the distance charging section, the toll collection system 1 only performs the process of recording the discrimination result of the vehicle type classification by the vehicle type discrimination device 4 and the entrance tollgate name in the vehicle AA (vehicle-mounted device α). and billing processing is not performed.

The vehicle AA is traveling on the lane LN that leads from the general road side to the expressway side via the entrance tollgate. An island IS is laid on both sides of the lane LN, and at least some of the various devices that make up the toll collection system 1 are installed.

Hereinafter, the direction in which the lane LN extends (±X direction in FIG. 1) is referred to as "lane direction". In addition, the expressway side in the lane direction of the lane LN (+X direction side in FIG. 1) is described as the “downstream side”, and the general road side in the lane direction of the lane LN (−X direction side in FIG. 1) is described as the “upstream side. ”.
Further, the width direction of the lane LN is referred to as the lane width direction (±Y direction in FIG. 1), and the vehicle height direction of the vehicle AA is referred to as the vertical direction (±Z direction in FIG. 1).

The toll collection system 1 according to the present embodiment performs wireless communication with the vehicle AA that has entered the lane LN, and performs charging processing according to the vehicle type classification of the vehicle AA. For example, the toll collection system 1 may be part of a system that constructs an electronic toll collection system (ETC: Electronic Toll Collection System (registered trademark), also referred to as an "automatic toll collection system").

As shown in FIGS. 1 and 2 , the toll collection system 1 includes a vehicle detector 2 , a communication antenna 3 , a vehicle type determination device 4 , and an axle number detection device 5 .
The toll collection system 1 also includes a billing processing unit (not shown) that manages a series of billing processes, and transmits information obtained through wireless communication and information on the determined billing amount to a remotely located central payment processing unit (not shown). output to the host device).

(Configuration of vehicle detector)
The vehicle detector 2 is a transmissive multi-optical axis sensor having a light projector 2A and a light receiver 2B. The light projector 2A and the light receiver 2B are installed so as to face each other across the lane LN at the entry detection position XA in the lane direction (±X direction). As a result, the vehicle detector 2 outputs a vehicle detection signal indicating the entry and exit of the vehicle AA traveling on the lane LN at the entry detection position XA of the lane LN.
In addition, the structure of the vehicle detector 2 is not limited to the said aspect. In other embodiments, the vehicle detector 2 may be, for example, a reflective multi-optical axis sensor, or a laser scanner that scans a single detection light (laser) over a wide range. good too.

(Configuration of communication antenna)
The communication antenna 3 performs wireless communication with the vehicle-mounted device α of the vehicle AA. Specifically, the communication antenna 3 is formed so as to be able to transmit and receive electromagnetic waves of a predetermined frequency (for example, about 5.8 GHz). communicate. Through this wireless communication, the identification information of the user who gets on the vehicle AA is acquired, and billing processing can be performed at the rear (central payment processing unit).
The communication antenna 3 is provided downstream of the entry detection position XA, and starts emitting electromagnetic waves when the vehicle detector 2 detects the entry of the vehicle AA, for example.

(Configuration of vehicle type discrimination device)
The vehicle type determination device 4 determines the vehicle type of the vehicle AA that has entered the lane LN based on various information (vehicle length, vehicle height, number of axles, license plate information, etc.) obtained through various sensors. The vehicle type category is, for example, classified into five categories of "light vehicle/motorcycle", "ordinary vehicle", "medium-sized vehicle", "large vehicle", and "extra-large vehicle".
Here, the vehicle type determination device 4 according to the present embodiment determines the vehicle type classification of the vehicle AA based on the number of axles detected by the axle number detection device 5 described later. For example, when it is found that the vehicle AA is classified as a freight vehicle based on license plate information or the like, the vehicle type determination device 4 further determines that it is a "large vehicle" when the number of axles is 4 or less. If the number is 5 or more, it is determined as an "extra-large car". This determination process is strictly based on the number of "grounded axles". Therefore, when detecting the number of axles of the vehicle AA, the axle number detection device 5 is required not to include an axle that is not grounded by the lift axle function.

(Configuration of axle number detector)
The axle number detection device 5 detects the number of axles (the number of grounded axles) of the vehicle AA.
The axle number detection device 5 has a photographing device 51 and a processing section 52 .

The photographing device 51 is installed on the island IS so as to photograph the side surface of the vehicle traveling on the lane LN. Moreover, the imaging device 51 is installed near the position XA in the lane direction. Based on the vehicle detection signal from the vehicle detector 2, the photographing device 51 continuously ( as video data).

The processing unit 52 detects the number of axles of the vehicle AA based on the photographed images (moving image data) continuously acquired by the photographing device 51 . Specific contents of the processing performed by the processing unit 52 will be described later.
In this embodiment, the processing unit 52 is illustrated as having a housing provided separately from the imaging device 51 and the like and installed on the island IS. It is not limited to this aspect. For example, the processing unit 52 may be integrated with the photographing device 51 , or the function of the processing unit 52 may be provided by the vehicle type determination device 4 .

(Functional configuration of processing unit)
A functional configuration of the processing unit 52 will be described with reference to FIG.
As shown in FIG. 2 , the processing section 52 has functions as an image acquisition section 521 , an area identification section 522 , a height acquisition section 523 , a lift-up axis determination section 524 and an axle number identification section 525 .
The image acquisition unit 521 acquires a side image of the vehicle AA through photographing by the photographing device 51 . The image acquisition unit 521 according to the present embodiment extracts frames and regions in which the tires of the vehicle AA are captured in a predetermined range from the moving image data obtained by the imaging device 51, and combines the regions in which each tire is captured in time series. to create a single lateral image. This processing by the image acquisition unit 521 will be described later.
The area identification unit 522 identifies the front area and the rear area of the vehicle AA in the side image acquired by the image acquisition unit 521 .
The height acquisition unit 523 acquires the image height of each tire of the vehicle AA included in the side image. More specifically, the height acquisition unit 523 according to the present embodiment acquires the height on the image of each tire belonging to the rear area of the vehicle AA.
The lift-up axis determination unit 524 is based on the position on the image of the tire belonging to the front region and the position on the image of the tire drawn at the lowest position among the tires belonging to the rear region on the side image. , a reference line is generated on the side image, and a tire separated from the reference line by a predetermined value or more is determined to be a lift-up axle (an axle that is not grounded by the lift axle function).
The number-of-axles identification unit 525 identifies the number of axles of the vehicle AA and transmits the result to the vehicle type identification device 4 . Specifically, axle number identifying unit 525 identifies the number of axles of vehicle AA by subtracting the number of lift-up axles from the total number of tires shown in the side image. Then, the number-of-axles identification unit 525 transmits the detection result of the number of axles for the vehicle AA to the vehicle type determination device 4 .

(Processing flow of toll collection system)
FIG. 3 is a diagram showing a processing flow of the toll collection system according to the first embodiment.
4 to 7 are explanatory diagrams showing the contents of processing of the toll collection system according to the first embodiment.
The flow of a series of processes executed by the toll collection system 1 will be described in detail below with reference to FIGS. 3 to 7. FIG.

The processing flow shown in FIG. 3 starts from the stage when the vehicle detector 2 detects the entry and exit of the vehicle AA at the entry detection position XA.
First, the image acquisition unit 521 of the processing unit 52 creates a side image including all the tires of the vehicle AA from the video data acquired by the imaging device 51 while the vehicle AA is running (step ST01).
Next, the area specifying unit 522 of the processing unit 52 specifies the front area and the rear area of the vehicle AA in the side image acquired in step ST01 (step ST02).

Here, details of the processing of steps ST01 and ST02 will be described with reference to FIGS. 4 and 5. FIG.

Since the installation position and imaging range (angle of view) of the imaging device 51 are limited, the entire side surface of a vehicle with a large vehicle length cannot be captured in one still image. Therefore, the toll collection system 1 according to the present embodiment acquires one side image including all the tires of the vehicle AA as follows.

First, based on the vehicle detection signal from the vehicle detector 2, the photographing device 51 detects that the rear end of the vehicle body of the vehicle AA is separated from the entry detection position XA from the time T0 when the front end of the vehicle body of the vehicle AA reaches the entry detection position XA. Shooting is performed continuously (as moving image data) until time T6. When the moving image data is acquired in this manner, the image acquiring unit 521 processes the moving image data to create a side image including all the tires of the vehicle AA.

Specifically, in step ST01, the image acquiring unit 521 obtains a predetermined range on the image of each frame (for example, a ) to identify the frame that contains the tire. Then, the image acquisition unit 521 cuts out and extracts a portion in the width direction (horizontal direction) including at least the entire tire from the specified frame. In the example shown in FIG. 4, the first tire of the vehicle AA is included in the predetermined range of the frame captured at time T1. Therefore, the image acquiring unit 521 acquires a partial image DT1 by extracting a portion in the width direction that includes the entire tire of the first axis from the frame captured at time T1.
Similarly, the image acquisition unit 521 obtains the entire tires of the 2nd, 3rd, 4th, and 5th axles of the vehicle AA from the frames captured at the time T2, the time T3, the time T4, and the time T5. By cutting out the regions in the width direction, partial images DT2 to DT5 are obtained.
Then, the image acquiring unit 521 combines the partial images DT1 to DT5 acquired as described above in time series while matching the positions of the partial images DT1 to DT5 in the height direction (vertical direction). A side image DT is created (see FIG. 5).

In subsequent step ST02, the area specifying unit 522 specifies the front area and the rear area of the vehicle AA in the side image DT. Specifically, the region specifying unit 522 determines the intermediate time between time T0 (time when the vehicle AA entered the entry detection position XA) and time T6 (time when the vehicle AA left the entry detection position XA). Calculate TM (TM=(T2+T6)/2) (see FIG. 4). Then, the region specifying unit 522 specifies, as a front region, a region of the side image DT that is cut out from the frames captured between the time T0 and the time TM. In addition, the region specifying unit 522 specifies a region clipped from frames captured between time TM and time T6 as a rear region. In the example shown in FIGS. 4 and 5, by the processing in step ST02, the area formed by the partial images DT1 and DT2 in the side image DT is specified as the front area, and is formed by the partial images DT3, DT4 and DT5. A region is identified as the posterior region.

Returning to FIG. 4, next, the height acquisition unit 523 of the processing unit 52 acquires the image height of each tire included in the side image DT (step ST03). The “height of the tire on the image” is, in other words, the drawing position of each tire in the vertical direction of the side image DT.

Here, the contents of the processing in step ST03 will be described in detail with reference to FIG.

The height acquisition unit 523 extracts the drawing area of each tire included in the side image DT by image recognition processing. Then, the height acquisition unit 523 identifies a reference position for each of the extracted drawing regions of each tire. In this embodiment, the "reference position" is the lowest position of the drawing area of each tire, but in other embodiments, the "reference position" is the center of the drawing area of each tire It may be the position, the position of the top end, or the like.
In the example shown in FIG. 6, the height acquisition unit 523 extracts the drawing area R1 of the tire of the first axis included in the side image DT, and further specifies the reference position SP1, which is the lowest position of the tire. . The height acquisition unit 523 similarly identifies the reference positions SP2 to SP5 for the other tires included in the side image DT.
Subsequently, the height acquisition unit 523 measures heights H1 to H5 on the image of the reference positions SP1 to SP5 specified as described above. Heights H1 to H5 are drawing positions in the vertical direction of each of the reference positions SP1 to SP5 when the lower end of the side image DT is set as a reference (0) (see FIG. 6). The heights H1-H5 may be expressed in "number of pixels", for example.

Returning to FIG. 4, next, the lift-up axis determination unit 524 of the processing unit 52 draws a reference line on the side image DT based on the reference positions SP1 to SP5 whose heights H1 to H5 are specified in step ST03. is generated (step ST04). Specifically, the lift-up axis determining unit 524 determines the lowest reference position on the image among all the reference positions for the tires belonging to the front area of the vehicle AA and the reference positions for the tires belonging to the rear area of the vehicle AA. and generate a reference line based on
Next, the lift-up axis determining section 524 of the processing section 52 identifies the lift-up axis based on the reference line generated in step ST04 (step ST05).

Here, the contents of the processing of steps ST04 and ST05 will be described in detail with reference to FIG.

In the example shown in FIG. 7, the reference positions corresponding to the tires belonging to the front region are two reference positions SP1 and SP2, and the reference positions corresponding to the tires belonging to the rear region are reference positions SP3, SP4 and SP5. There are three.
In step ST04, the lift-up axis determination unit 524 refers to the heights H3, H4, and H5 of the reference positions SP3, SP4, and SP5 belonging to the rear region among the heights H1 to H5 measured in step ST03, A reference position, which is the lowest position on the image among these, is specified. In the example shown in FIG. 7, it is assumed that the reference position SP4 is specified.
Next, the lift-up axis determination unit 524 generates the reference line SL based on the two reference positions SP1 and SP2 belonging to the front region and the lowest reference position SP4 among the reference positions belonging to the rear region. This reference line SL is generated, for example, so that the sum of squares of distances from each of the reference positions SP1, SP2, and SP4 is minimized (that is, by the least-squares method).

In step ST05, the lift-up axis determination unit 524 determines each reference position (reference position SP3, SP5) other than the reference positions (reference positions SP1, SP2, SP4) used to generate the reference line SL. Calculate the distance from the position to the reference line SL. In the example shown in FIG. 7, the lift-up axis determination unit 524 calculates a distance D3 from the reference position SP3 to the reference line SL and a distance D5 from the reference position SP5 to the reference line SL.
Furthermore, the lift-up axis determination unit 524 determines whether or not the calculated distance D3 or distance D5 exceeds the determination threshold value Dth. When the distance D3 exceeds the determination threshold value Dth, the lift-up axis determination unit 524 determines that the tire associated with the reference position SP3 is the lift-up axis. Similarly, when the distance D5 exceeds the determination threshold value Dth, the lift-up axis determination unit 524 determines that the tire associated with the reference position SP5 is the lift-up axis. On the other hand, when the distances D3 and D5 are equal to or less than the determination threshold value Dth, the lift-up axis determination unit 524 determines that the tires related to the reference positions SP3 and SP5 are not the lift-up axis.
The "determination threshold value Dth" may be a predetermined fixed value, or may be determined according to the correlation coefficient of the regression line (reference line SL) obtained by the least squares method for the reference positions SP1, SP2, and SP4. may be determined by

Returning to FIG. 4, next, the number-of-axles identification unit 525 of the processing unit 52 subtracts the number of lift-up axles identified in step ST05 from the total number of tires included in the side image DT. is specified (step ST06).
The number-of-axles identification unit 525 transmits the detection result of the number of axles for the vehicle AA to the vehicle type determination device 4 .

(action, effect)
As described above, the axle number detection device 5 according to the first embodiment includes the image acquisition unit 521 that acquires the side image DT of the vehicle, and the area identification unit that identifies the front area and the rear area of the vehicle in the side image DT. 522, the position on the side image DT of the tire belonging to the front region, and the position on the side image DT of the tire drawn at the lowest position among the tires belonging to the rear region. A lift-up axis determination unit 524 that generates a reference line SL and determines a tire that is separated from the reference line SL by a predetermined value or more as a lift-up axis.

The number and positions of liftable axles (which axles are lifted) of vehicles having a lift axle function vary from vehicle to vehicle. However, in any vehicle, the axle to be lifted up is always one or a plurality of tires arranged on the rear side (rear area) of the vehicle, and on the front side (front area) of the vehicle. The placed tires are never lifted up. Also, it is impossible for all rear tires to be lifted up, and at least one axle must always be grounded.
In view of such a fact, the axle number detection device 5 according to the present embodiment has the above-described configuration, so that the tire on the front side (the tire that is always in contact with the ground) and the tire on the rear side, which is the lowest A reference line SL is generated based on (a tire on the rear side that is most likely to be in contact with the ground). Then, the axle number detection device 5 determines whether or not each tire is a lift-up axle based on the positional relationship with the reference line SL thus generated. As a result, the relative positional relationship between the grounded tire and the lifted tire is clarified via the reference line SL. is lifted up, the determination can be made with high accuracy.
Further, for example, when the reference line SL is generated based only on the front tire of the vehicle AA, the error when extending the reference line SL to the rear side of the vehicle AA becomes large, and the rear tire It is assumed that the accuracy of determination as to whether or not the vehicle is lifted up is lowered. However, according to the axle number detection device 5 according to the present embodiment, the reference line SL is generated based on at least both the front tire and the rear tire of the vehicle AA. can be enhanced.

As described above, according to the axle number detection device 5 according to the first embodiment, it is possible to make it difficult to erroneously detect the number of axles of the grounded tire.

Further, according to the axle number detection device 5 according to the first embodiment, the region identification unit 522 can detect the entire passing time zone of the vehicle AA (the time T0 in FIG. 4) at the predetermined position (the entry detection position XA) on the lane LN. The area of the side image DT acquired in the first half of the time period (time T0 to time T6) is defined as the front area, and the area of the side image DT acquired in the first half of the time period (time T0 to time T6) is defined as the front area. ) is specified as the rear region.
By doing so, each tire included in the side image DT belongs to the front region of the vehicle AA or belongs to the rear region based on the passage time zone of the vehicle at a predetermined position (entry detection position XA) on the lane LN. belonging can be identified.

Further, according to the axle number detection device 5 according to the first embodiment, the image acquisition unit 521 acquires the vehicle data from the moving image data (data consisting of a bundle of a plurality of still images) acquired while the vehicle AA is running. A side image DT is acquired by combining partial images (partial images DT1 to DT5 shown in FIGS. 4 and 5) cut out so as to include the tires from frames including the tires of AA.
By doing so, even if the photographing device 51 cannot capture the entire vehicle body of the vehicle AA in one still image, it is possible to acquire the side image DT including all the tires of the vehicle AA. can.

(First Modification of First Embodiment)
FIG. 8 is an explanatory diagram showing details of processing of the toll collection system according to the first modification of the first embodiment.
The configuration of the toll collection system 1 according to this modification is the same as that of the first embodiment. However, the lift-up axis determination unit 524 of the processing unit 52 according to the present modification determines the position on the side image DT of the tire drawn at the lowest position among the tires belonging to the front region, and the position of the tire belonging to the rear region. A reference line SL is generated based on the position on the side image DT of the tire drawn at the lowest position.

Specifically, in step ST04 of FIG. 3, the lift-up axis determination section 524 identifies the lowest reference position on the image, out of the reference positions SP1 and SP2 corresponding to the tire belonging to the front region. In the example shown in FIG. 8, it is assumed that the reference position SP1 is identified.
Next, the lift-up axis determination unit 524 identifies the lowest reference position on the image among the reference positions SP3, SP4, and SP5 corresponding to the tire belonging to the rear area. In the example shown in FIG. 8, it is assumed that the reference position SP4 is identified.
Then, the lift-up axis determination unit 524 generates a straight line connecting the reference position SP1 identified from the front region and the reference position SP4 identified from the rear region as the reference line SL.

Next, in step ST05 in FIG. 3, the lift-up axis determination unit 524 determines the reference positions (reference positions SP2, SP3, SP5) other than the reference positions (reference positions SP1, SP4) used to generate the reference line SL. , the distance from each reference position to the reference line SL is calculated. In the example shown in FIG. 8, the lift-up axis determination unit 524 determines the distance D2 from the reference position SP2 to the reference line SL, the distance D3 from the reference position SP3 to the reference line SL, and the distance D3 from the reference position SP5 to the reference line SL. Calculate the distance D5.
Furthermore, the lift-up axis determination unit 524 identifies the lift-up axis based on the determination result of whether or not each of the calculated distances D2, D3, and D5 exceeds the determination threshold value Dth.

By doing so, the reference line SL is generated based on both the front tire and the rear tire of the vehicle AA, so the accuracy of determination can be improved. In addition, since the reference line SL may be generated by connecting the reference positions of the tire selected one by one from the front region and the rear region, it is possible to simplify the process of determining the lift-up axis.

(Second modification of the first embodiment)
9 and 10 are explanatory diagrams showing details of processing of the toll collection system according to the second modification of the first embodiment.

The configuration of the toll collection system 1 according to this modification is the same as that of the first embodiment. However, the photographing device 51 of the toll collection system 1 according to this modified example is equipped with a cylindrical lens (a lens formed in a cylindrical shape) to photograph the image of the vehicle body side surface of the vehicle AA compressed in the vehicle length direction. (See FIG. 9). As a result, the entire side surface of a vehicle with a large vehicle length can be included in one image.

The image acquisition unit 521 according to this modification acquires one side image DT in which the body of the vehicle AA traveling on the lane LN is compressed in the vehicle length direction and includes the entire vehicle body, as shown in FIG.
In this case, the photographing device 51 may take a mode in which one still image (side image DT) is photographed at a timing according to the vehicle detection signal instead of photographing the vehicle AA as moving image data.

Further, the area specifying unit 522 according to the present modification divides a single side image DT as shown in FIG. The area on the left side of the image (area including the rear side of the vehicle body) is specified as the rear area.

Further, the height acquisition unit 523 according to this modification extracts the drawing area of each tire included in the side image DT, and further specifies the reference positions SP1 to SP5, which are the positions of the lowest ends thereof. Subsequently, the height acquisition unit 523 measures the heights H1 to H5 on the image of the reference positions SP1 to SP5 of each tire (see FIG. 6).

Further, as shown in FIG. 10, the lift-up axis determination unit 524 according to this modification specifies the lowest reference position on the image among the reference positions SP3, SP4, and SP5 belonging to the rear region. In the example shown in FIG. 10, it is assumed that the reference position SP4 is specified.
Next, the lift-up axis determination unit 524 generates the reference line SL based on the two reference positions SP1 and SP2 belonging to the front region and the lowest reference position SP4 among the reference positions belonging to the rear region. As in the first embodiment, this reference line SL is generated such that the sum of squares of distances from each of the reference positions SP1, SP2, and SP4 is minimized.
Then, the lift-up axis determination unit 524 measures the distances D3 and D5 between the reference positions SP3 and SP5 and the reference line SL, and determines whether or not the distances D3 and D5 exceed the determination threshold value Dth. to identify the lift-up axis.

As described above, in the second modification of the first embodiment, by adding a configuration (such as a cylindrical lens) that allows the entire vehicle body to be included in one side image DT, only the one side image DT is added. The lift-up axis can be identified based on Thereby, the simplification of the whole axle number detection process can be achieved.

Note that the cylindrical lens included in the imaging device 51 according to the second modification is an example of a configuration that enables the entire vehicle body of the vehicle AA traveling on the lane LN to be included in one side image DT. Embodiments are not limited to this. An imaging device 51 according to another embodiment may be, for example, provided with a concave reflecting mirror.
Further, the photographing device 51 according to another embodiment does not need to be equipped with a special configuration such as a cylindrical lens. It may be a mode installed in.

<Second embodiment>
The toll collection system according to the second embodiment will be described in detail below with reference to FIGS. 11 to 13. FIG.

(Configuration of toll collection system)
FIG. 11 is a diagram showing the functional configuration of a toll collection system according to the second embodiment.
As shown in FIG. 11, the processing unit 52 of the toll collection system 1 according to the second embodiment includes an image acquiring unit 521, a height acquiring unit 523, a lift-up axis determining unit 524, an axle number specifying unit 525, and a low position It has a function as the tire specifying section 526 .
The low-position tire specifying unit 526 specifies the two lowest tires among the plurality of tires whose heights are acquired by the height acquiring unit 523 .
In the following description, other functions of the processing unit 52 are assumed to be the same as in the first embodiment.

(Processing flow of toll collection system)
FIG. 12 is a diagram showing the processing flow of the toll collection system according to the second embodiment.
Also, FIG. 13 is an explanatory diagram showing the details of the processing of the toll collection system according to the second embodiment.
Hereinafter, the flow of a series of processes executed by the toll collection system 1 according to the second embodiment will be described in detail with reference to FIGS. 12 and 13. FIG.

The processing flow shown in FIG. 12 starts from the stage when the vehicle detector 2 detects the entry and exit of the vehicle AA at the entry detection position XA.

First, the image acquisition unit 521 of the processing unit 52 creates a side image including all the tires of the vehicle AA from the moving image data acquired by the imaging device 51 while the vehicle AA is running (step ST11). The processing of this step S11 is the same as that of the first embodiment (step ST01 of FIG. 3, FIGS. 4 and 5), so detailed description thereof will be omitted.

Next, the height acquisition unit 523 of the processing unit 52 acquires the image heights of all the tires included in the side image DT (similar to that shown in FIG. 5) (step ST12). Since the process of step S12 is the same as that of the first embodiment (step ST03 in FIG. 3, FIG. 6), detailed description thereof will be omitted.

Next, the low-position tire specifying unit 526 of the processing unit 52 refers to the height of each tire on the image obtained in step ST12, and specifies the reference positions of the two tires drawn at the lowest position. (Step ST13).
Next, the lift-up axis determination section 524 of the processing section 52 generates a reference line on the side image DT based on the reference positions of the two tires identified in step ST13 (step ST14). Then, the lift-up axis determining section 524 identifies the lift-up axis based on the reference line generated in step ST14 (step ST15).

Here, details of the processing of steps ST13 to ST15 will be described with reference to FIG.

In step ST13, the low-position tire identifying section 526 identifies the two lowest reference positions by referring to the heights H1 to H5 on the image of each of the reference positions SP1 to SP5. In the example shown in FIG. 13, it is assumed here that the reference position SP2 and the reference position SP4 are identified.
Next, in step ST14, the lift-up axis determination section 524 generates a straight line connecting the reference position SP2 and the reference position SP4 as the reference line SL.
Then, in step ST15, the lift-up axis determination section 524 measures the distances D1, D3, and D5 to the reference line SL for the reference points SP1, SP3, and SP5 other than the reference positions SP2 and SP4. The lift-up axis determination unit 524 determines whether or not each tire is a lift-up axis based on whether each of the distances D1, D3, and D5 exceeds a predetermined determination threshold.

Returning to FIG. 12, next, the number-of-axles identification unit 525 of the processing unit 52 subtracts the number of lift-up axles identified in step ST15 from the total number of tires included in the side image DT. is specified (step ST16).
The number-of-axles identification unit 525 transmits the detection result of the number of axles for the vehicle AA to the vehicle type determination device 4 .

(action, effect)
As described above, the axle number detection device 5 according to the second embodiment includes the image acquisition unit 521 that acquires the side image DT of the vehicle AA, and the height above the side image DT of each tire included in the side image DT. A height acquisition unit 523 to acquire, a low position tire specifying unit 526 to specify the two lowest tires among the plurality of tires whose heights are acquired, and a reference line SL connecting each reference point of the two lowest tires and a lift-up axis determination unit 524 that determines a tire that is separated from the reference line SL by a predetermined value or more as a lift-up axis.

If any axle of a vehicle with lift axle functionality is lifted up, at least two tires should be on the ground. Therefore, as in the above configuration, by specifying the two tires drawn at the lowest position on the side image DT, a reference line SL connecting two tires that are likely to be in contact with the ground is generated. can be done. As a result, the relative positional relationship between the grounded tire and the lifted tire is clarified via the reference line SL. is lifted up, the determination can be made with high accuracy.
In addition, since the process of generating the reference line SL is simpler than in the first embodiment (and its modification), the overall process of detecting the number of axles can be simplified.

<Third Embodiment>
The toll collection system according to the third embodiment will be described in detail below with reference to FIGS. 14 to 17. FIG.

FIG. 14 is a diagram showing the functional configuration of a toll collection system according to the third embodiment.
As shown in FIG. 14, the processing unit 52 of the toll collection system 1 according to the third embodiment includes an image acquisition unit 521, a height acquisition unit 523, a lift-up axis determination unit 524, an axle number determination unit 525, and a distribution determination unit. It has a function as the part 527 .
The distribution specifying unit 527 creates a histogram showing the number of tires for each height section in the side image DT, and the first group in the histogram and the section higher than the first group (higher than the first group). A second group (distributed in locations) is identified.
In the following description, other functions of the processing unit 52 are assumed to be the same as in the first embodiment.

(Processing flow of toll collection system)
FIG. 15 is a diagram showing the processing flow of the toll collection system according to the third embodiment.
16 and 17 are explanatory diagrams showing the contents of the processing of the toll collection system according to the third embodiment.
Hereinafter, the flow of a series of processes executed by the toll collection system 1 according to the third embodiment will be described in detail with reference to FIGS. 15 to 17. FIG.

The processing flow shown in FIG. 15 starts from the stage when the vehicle detector 2 detects the entry and exit of the vehicle AA at the entry detection position XA.

First, the image acquisition unit 521 of the processing unit 52 creates a side image including all the tires of the vehicle AA from the video data acquired by the imaging device 51 while the vehicle AA is running (step ST21). The processing of this step S11 is the same as that of the first embodiment (step ST01 of FIG. 3, FIGS. 4 and 5), so detailed description thereof will be omitted.

Next, the height acquisition unit 523 of the processing unit 52 acquires the image heights of all the tires included in the side image DT (step ST22).

Next, the distribution specifying unit 527 of the processing unit 52 creates a histogram indicating the number of tires for each height section in the side image DT (step ST23).
Furthermore, the distribution identifying unit 527 identifies the first group in the histogram created in step ST23 and the second group distributed at a higher position than the first group (step ST24).
The lift-up axis determination unit 524 of the processing unit 52 determines the tire belonging to the second group identified in step ST24 as the lift-up axis (step ST25).

Here, details of the processing of steps ST23 to ST25 will be described with reference to FIGS. 16 and 17. FIG.

In step ST23, the distribution identifying unit 527 defines height sections at regular intervals ΔH in the height direction with respect to the side image DT (see FIG. 16).
Next, the distribution identifying unit 527 refers to the heights H1 to H5 on the image of each of the reference positions SP1 to SP5, determines which height section each reference position belongs to, and obtains a histogram for each height section. is created (see FIG. 17).

In step ST24, the distribution specifying unit 527 determines whether or not the histogram is bimodal by determining whether or not there is a "valley of distribution" as shown in FIG.
When it is determined that the histogram is bimodal, the distribution identifying unit 527 further divides the "valley of the distribution" into a first group G1 distributed on the lower side and a second group G2 distributed on the higher side. identify.

In step ST25, the lift-up axis determination section 524 identifies the tires belonging to the second group G2 as the lift-up axis. In the example shown in FIGS. 16 and 17, the lift-up axis determination unit 524 selects the tires (third and fifth axis tires) related to the reference position SP3 and the reference position SP5 belonging to the second group G2 as the lift-up axis. Identify as

Returning to FIG. 15, next, the axle number specifying unit 525 of the processing unit 52 subtracts the number of lift-up axles specified in step ST25 from the total number of tires included in the side image DT, thereby determining the vehicle AA. is specified (step ST26).
The number-of-axles identification unit 525 transmits the detection result of the number of axles for the vehicle AA to the vehicle type determination device 4 .

(action, effect)
As described above, the axle number detection device 5 according to the third embodiment includes the image acquisition unit 521 that acquires the side image DT of the vehicle AA, and the height of each of the plurality of tires included in the side image DT on the side image DT. A height acquisition unit 523 that acquires the height and a histogram showing the number of tires for each height section in the side image DT is created, and the first group G1 in the histogram and the positions higher than the first group G1 are distributed. and a lift-up axis determination unit 524 that determines tires belonging to the second group G2 among the plurality of tires included in the side image DT as lift-up axes. Prepare.

If any axle of a vehicle with lift axle functionality is lifted up, at least two tires should be on the ground. Therefore, by grouping the tires by height section using a histogram as in the above configuration, it is possible to find the distribution of the heights of the tires that are in contact with the ground. Here, if there is a tire that is lifted up, the tire should be distributed at a higher position than the group of tires that are grounded.
Therefore, it is determined whether or not each tire is lifted up based on the relative distribution relationship with the grounded tire, so that determination can be made with high accuracy.

In the first to third embodiments (and each modified example), various processes of the axle number detection device 5 described above are stored in a computer-readable recording medium in the form of a program. The various processes described above are performed by the computer reading and executing the program. Computer-readable recording media include magnetic disks, magneto-optical disks, CD-ROMs, DVD-ROMs, semiconductor memories, and the like. Alternatively, the computer program may be distributed to a computer via a communication line, and the computer receiving the distribution may execute the program.

The program may be for realizing part of the functions described above. Furthermore, it may be a so-called difference file (difference program) that can realize the above functions by combining with a program already recorded in the computer system.

In another embodiment, a part of each functional part of the axle number detection device 5 described in the first to fourth embodiments is provided in another computer connected via a network. good too.

As described above, several embodiments according to the present invention have been described, but all these embodiments are presented as examples and are not intended to limit the gist and technical scope of the invention. These embodiments can be implemented in various other forms, and various omissions, replacements, and modifications can be made without departing from the gist and technical scope of the invention.

<Appendix>
The axle number detection device 5, the toll collection system 1, the axle number detection method, and the program described in each embodiment are grasped, for example, as follows.

(1) The axle number detection device 5 according to the first aspect includes an image acquisition unit 521 that acquires the side image DT of the vehicle AA, and an area identification unit that identifies the front area and the rear area of the vehicle AA in the side image DT. 522, the position on the side image DT of the tire belonging to the front region, and the position on the side image DT of the tire drawn at the lowest position among the tires belonging to the rear region. A lift-up axis determination unit 524 that generates a reference line SL and determines a tire that is separated from the reference line SL by a predetermined value or more as a lift-up axis.
By doing so, the relative positional relationship between the grounded tire and the lifted tire is clarified via the reference line SL. Based on this, it is determined whether or not each tire is lifted up, so determination can be made with high accuracy.

(2) The number-of-axles detection device 5 according to the second aspect is the number-of-axles detection device of (1), in which the area specifying unit 522 determines the entire passage time zone of the vehicle AA at a predetermined position on the lane LN (time The area of the side image DT acquired in the first half of the time period (time T0 to time T6) is defined as the front area, and the area of the side image DT acquired in the latter half of the entire transit time period (time TM to time T6) is defined as the front area. The area of the acquired side image DT is specified as the rear area.
By doing so, each tire included in the side image DT belongs to the front region of the vehicle AA or belongs to the rear region based on the passage time zone of the vehicle at a predetermined position (entry detection position XA) on the lane LN. belonging can be specified.

(3) The number-of-axles detection device 5 according to the third aspect is the number-of-axles detection device of (1) or (2), and the image acquisition unit 521 is configured to obtain moving image data acquired while the vehicle AA is running. The side image DT is obtained by combining the partial images DT1 to DT5 cut out so as to include the tire from each frame including the tire of the vehicle AA.
By doing so, even if the photographing device 51 cannot capture the entire vehicle body of the vehicle AA in one still image, it is possible to acquire the side image DT including all the tires of the vehicle AA. can.

(4) The axle number detection device 5 according to the fourth aspect is the axle number detection device according to any one of (1) to (3), and the lift-up axle determination unit 524 is one of the tires belonging to the front region. A reference line SL is generated based on the position on the side image DT of the tire drawn at the lowest position and the position on the side image DT of the tire drawn at the lowest position among the tires belonging to the rear area. .
By doing so, the reference line SL is generated based on both the front tire and the rear tire of the vehicle AA, so the accuracy of determination can be improved. In addition, since the reference line SL may be generated by connecting the reference positions of the tire selected one by one from the front region and the rear region, it is possible to simplify the process of determining the lift-up axis.

(5) The axle number detection device 5 according to the fifth aspect includes an image acquisition unit 521 that acquires the side image DT of the vehicle AA, and acquires the height of each tire included in the side image DT on the side image DT. A height acquisition unit 523, a low-position tire identification unit 526 that identifies the two lowest tires among a plurality of tires whose heights have been obtained, and a reference line SL that connects the reference points of the two lowest tires is generated. and a lift-up axis determination unit 524 that determines a tire that is separated from the reference line SL by a predetermined value or more as a lift-up axis.
By doing so, the relative positional relationship between the grounded tire and the lifted tire is clarified, and each tire is lifted up based on the clarified positional relationship. Since it is determined whether or not it is set, the determination can be performed with high accuracy. In addition, since the process of generating the reference line SL is simple, the whole process of detecting the number of axles can be simplified.

(6) The axle number detection device 5 according to the sixth aspect includes the image acquisition unit 521 that acquires the side image DT of the vehicle AA, and the height above the side image DT of each of the plurality of tires included in the side image DT. The height acquisition unit 523 to acquire and a histogram showing the number of tires for each height section in the side image DT are created, and the first group G1 in the histogram and the second group G1, which is a section higher than the first group G1, are created. and a lift-up axis determination unit 524 that determines tires belonging to the second group G2 among the plurality of tires included in the side image DT as lift-up axes.
In this way, by grouping the tires by height interval using the histogram, it is possible to find the respective distributions of the height of the grounded tires and the lifted tires. Since it is determined whether or not each tire is lifted up based on such a distribution relationship, it is possible to perform determination with high accuracy.

1 Toll collection system 2 Vehicle detector 3 Communication antenna 4 Vehicle type discrimination device 5 Axle number detection device 51 Photographing device 52 Processing unit 521 Image acquisition unit 522 Area identification unit 523 Height acquisition unit 524 Lift-up axis determination unit 525 Axle number identification unit 526 low position tire identification unit 527 distribution identification unit

Claims (11)

an image acquisition unit that acquires a side image of the vehicle;
a region identifying unit that identifies a front region and a rear region of the vehicle in the side image;
a height acquisition unit that acquires a height on the image of each tire belonging to the rear region;
means for specifying a tire drawn at the lowest height position on the image among the tires belonging to the rear region;
Based on the position on the side image of the tire belonging to the front region and the position on the side image of the tire drawn at the lowest position among the tires belonging to the rear region, a lift-up axis determination unit that generates a reference line and determines a tire that is separated from the reference line by a predetermined value or more as a lift-up axis;
Axle number detector. The region specifying unit
The area of the side image acquired in the first half of the entire passage time period of the vehicle at a predetermined position on the lane is defined as the front area, and the area of the side image acquired in the latter half of the entire passage time period is defined as the front area. The axle number detection device according to claim 1, wherein an area of a side image is specified as the rear area. The image acquisition unit is
2. The side image is obtained by combining partial images cut out from frames containing each tire of the vehicle, from video data obtained while the vehicle is running, so as to include the tire. The axle number detection device according to claim 2. The lift-up axis determination unit includes:
a position on the side image of the tire drawn at the lowest position among the tires belonging to the front region, and a position on the side image of the tire drawn at the lowest position among the tires belonging to the rear region; The axle number detection device according to any one of claims 1 to 3, wherein the reference line is generated based on. an image acquisition unit that acquires a side image of the vehicle;
a height acquisition unit that acquires the height of each tire included in the side image on the side image;
a low-position tire identification unit that identifies the two lowest tires among the plurality of tires whose heights are acquired;
a lift-up axis determination unit that generates a reference line connecting the reference points of the two lowest tires and determines a tire that is separated from the reference line by a predetermined value or more as a lift-up axis;
Axle number detector. an image acquisition unit that acquires a side image of the vehicle;
a height acquisition unit that acquires a height on the side image of each of a plurality of tires included in the side image;
a distribution identifying unit that creates a histogram indicating the number of tires for each height section in the side image, and identifies a first group and a second group that is a section higher than the first group in the histogram;
a lift-up axis determination unit that determines a tire belonging to the second group among the plurality of tires included in the side image as a lift-up axis;
Axle number detector. The axle number detection device according to any one of claims 1 to 6;
a vehicle type discrimination device that discriminates a vehicle type classification of the vehicle based on the number of axles detected by the axle number detection device;
toll collection system. obtaining a side image of the vehicle;
identifying a front region and a rear region of the vehicle in the side image;
obtaining a height on the image of each tire belonging to the rear region;
identifying a tire drawn at the lowest height position on the image among the tires belonging to the rear region;
Based on the position on the side image of the tire belonging to the front region and the position on the side image of the tire drawn at the lowest position among the tires belonging to the rear region, a step of generating a reference line and determining a tire separated from the reference line by a predetermined value or more as a lift-up axis;
A method for detecting the number of axles. In the computer of the axis number detection device,
obtaining a side image of the vehicle;
identifying a front region and a rear region of the vehicle in the side image;
obtaining a height on the image of each tire belonging to the rear region;
identifying a tire drawn at the lowest height position on the image among the tires belonging to the rear region;
Based on the position on the side image of the tire belonging to the front region and the position on the side image of the tire drawn at the lowest position among the tires belonging to the rear region, a step of generating a reference line and determining a tire separated from the reference line by a predetermined value or more as a lift-up axis;
program to run. an image acquisition unit that acquires a side image of the vehicle;
a region identifying unit that identifies a front region and a rear region of the vehicle in the side image;
A reference is drawn on the side image based on the position on the side image of the tire belonging to the front region and the position on the side image of the tire drawn at the lowest position among the tires belonging to the rear region. a lift-up axis determination unit that generates a line and determines that a tire that is separated from the reference line by a predetermined value or more is a lift-up axis;
equipped with
The region specifying unit
The area of the side image acquired in the first half of the entire passage time period of the vehicle at a predetermined position on the lane is defined as the front area, and the area of the side image acquired in the latter half of the entire passage time period is defined as the front area. identifying a region of a lateral image as the rear region;
Axle number detector. an image acquisition unit that acquires a side image of the vehicle;
a region identifying unit that identifies a front region and a rear region of the vehicle in the side image;
A reference is drawn on the side image based on the position on the side image of the tire belonging to the front region and the position on the side image of the tire drawn at the lowest position among the tires belonging to the rear region. a lift-up axis determination unit that generates a line and determines that a tire that is separated from the reference line by a predetermined value or more is a lift-up axis;
with
The image acquisition unit is
The side image is obtained by combining partial images cut out from frames including each tire of the vehicle, from video data obtained while the vehicle is running, so as to include the tires.
Axle number detector.

Images