JP7334541B2 - Road surface information measuring device, road surface information measuring method and program - Google Patents

Description

The present invention relates to a road surface information measuring device, a road surface information measuring method, and a program.

Conventionally, a method for calculating the speed of a vehicle (hereinafter also referred to as "vehicle speed") is known. For example, a method has been proposed in which a vehicle is detected from each of a plurality of imaging frames obtained by imaging at predetermined sample intervals, and the vehicle speed is calculated based on the vehicle detection results. As an example, based on known intervals between a plurality of white lines drawn on the road and intervals in an image between the plurality of white lines, correspondence (calibration) between the distance in the real space and the distance in the image is performed in advance. A method of calculating the vehicle speed from the movement vector of the vehicle in the image based on the association has been proposed (see, for example, Patent Document 1).

A method of calculating a plane in which a vehicle moves is also known. For example, the distance in real space between a plurality of markers mounted on a vehicle is measured in advance, and based on the coordinate values in the image of the plurality of markers and the distance in real space between the plurality of markers, A technique is known in which the three-dimensional coordinate positions of a plurality of mounted markers at a monitoring location are calculated, and a plane along which the vehicle moves is calculated from the three-dimensional coordinate positions (see Patent Document 2, for example).

Japanese Patent No. 3742410 Japanese Patent No. 3897984

However, if the correspondence between the distance in the real space and the distance in the image is required in advance (calibration), calibration is required for each installation point of the camera, which makes the calibration work cumbersome. turn into. In particular, when roads are blocked, there is a possibility that the calibration will not be performed as planned. In addition, it takes time and effort to measure the distance in the real space.

Accordingly, the present invention has been made in view of the above problems, and an object of the present invention is to calculate a vehicle speed without previously associating the distance in the real space with the distance in the image. It is to provide possible technology.

In order to solve the above problem, according to one aspect of the present invention, a vehicle detection unit that detects a vehicle traveling on a road surface based on a captured image, a vehicle type determination unit that determines the vehicle type as a vehicle type, and a road surface information acquisition unit that acquires information about the road surface corresponding to the vehicle type and information about the length of the vehicle; a movement vector calculation unit that calculates a movement vector of the vehicle based on a plurality of imaging frames; and the movement vector. and a vehicle speed calculation unit that calculates the speed of the vehicle based on the information about the road surface, and the information about the length of the vehicle includes a first length and a second length of the vehicle corresponding to the vehicle type. and the information on the road surface is an angle between the road surface and an imaging plane of a camera that captures the captured image .

The vehicle speed calculation unit may calculate a movement vector in space from the movement vector and information about the road surface, calculate a movement vector per unit time from the movement vector in space, and calculate the speed of the vehicle. .

The first length may be the length of the long side of the circumscribing rectangle of the vehicle in the captured image, and the second length may be the length of the short side of the circumscribing rectangle.

The first length may be the horizontal length of the license plate in the captured image, and the second length may be the vertical length of the license plate.

The road surface information acquisition unit may calculate an angle between the horizontal plane and the road surface based on an angle between the imaging plane and the road surface and an angle between the horizontal plane and the imaging plane measured in advance.

According to another aspect of the present invention, detecting a vehicle traveling on a road surface based on a captured image; calculating a movement vector of the vehicle based on a plurality of imaging frames; and calculating the movement vector of the vehicle based on the movement vector and the information on the road surface. calculating a speed, wherein the vehicle length information is a ratio between a first length and a second length of the vehicle corresponding to the vehicle type, and the road surface information is the captured image; A road surface information measuring method is provided , which is an angle between an imaging plane of a camera that captures an image and the road surface .

According to another aspect of the present invention, the computer comprises a vehicle detection unit that detects a vehicle traveling on a road surface based on a captured image, a vehicle type determination unit that determines the vehicle type as a vehicle type, and a vehicle type determination unit that determines the vehicle type. a road surface information acquisition unit that acquires information on the road surface corresponding to information on the length of a predetermined portion of the vehicle; a movement vector calculation unit that calculates a movement vector of the vehicle based on a plurality of imaging frames; a vehicle speed calculation unit that calculates the speed of the vehicle based on the vector and the information about the road surface , and the information about the length of the vehicle includes a first length and a second length of the vehicle corresponding to the vehicle type. and the information on the road surface is the angle between the imaging plane of the camera that captures the captured image and the road surface .

As described above, according to the present invention, there is provided a technique capable of calculating the vehicle speed without previously associating the distance in the real space with the distance in the image.

BRIEF DESCRIPTION OF THE DRAWINGS It is a figure for demonstrating the outline|summary of the road surface information measuring system which concerns on embodiment of this invention. It is a figure for demonstrating the outline|summary of the road surface information measuring system which concerns on the same embodiment. It is a figure for demonstrating the outline|summary of the road surface information measuring system which concerns on the same embodiment. It is a figure which shows the example of the captured image imaged with the camera. It is a figure which shows the example of the captured image imaged with the camera. It is a figure which shows the example of the captured image imaged with the camera. 1 is a block diagram showing the functional configuration of a road surface information measuring system according to an embodiment of the present invention; FIG. It is a figure which shows the example of vehicle information. It is a figure which shows the hardware constitutions of the information processing apparatus as an example of the road surface information measuring apparatus which concerns on embodiment of this invention.

Preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings. In the present specification and drawings, constituent elements having substantially the same functional configuration are denoted by the same reference numerals, thereby omitting redundant description.

In addition, in this specification and drawings, a plurality of components having substantially the same functional configuration are distinguished by attaching different numerals after the same reference numerals. In addition, similar components in different embodiments are distinguished from each other by using the same reference numerals followed by different alphabets. However, when there is no particular need to distinguish between a plurality of constituent elements having substantially the same functional configuration, only the same reference numerals are used.

<1. Details of Embodiment>
Details of embodiments of the present invention will be described.

[1-1. System overview]
First, an outline of a road surface information measuring system according to an embodiment of the present invention will be described. 1 to 3 are diagrams for explaining an overview of a road surface information measuring system according to an embodiment of the present invention. As shown in FIGS. 1 to 3, the road surface information measuring system 1 according to the embodiment of the present invention has a road surface information measuring device 10 and a camera 30. FIG. The camera 30 is connected to the road surface information measuring device 10 wirelessly or by wire. However, the camera 30 may not exist outside the road surface information measuring device 10 and may be incorporated inside the road surface information measuring device 10 .

The camera 30 obtains moving image data by capturing a plurality of continuous imaging frames in time series. In the embodiment of the present invention, when the vehicle 50 traveling on the road surface F1 from the back side to the front side enters a predetermined imaging area, the camera 30 is positioned at an angle that looks down on the vehicle 50 from diagonally above. is mainly assumed to be imaged from the front. However, the positional relationship between the imaging direction of the camera 30 and the traveling direction of the vehicle 50 is not limited. For example, the camera 30 may capture an image of the vehicle 50 traveling from the front to the back on the road surface F1 from behind.

Moreover, in the embodiment of the present invention, it is mainly assumed that the camera 30 is provided above the road surface F1. However, the installation position of the camera 30 is not limited. For example, camera 30 may be installed on the side of a road. Moving image data captured by the camera 30 is provided to the road surface information measuring device 10 . In the following description, for the sake of simplicity, the slope of the road surface on which the vehicle 50 travels does not matter (that is, whether the vehicle 50 travels on a horizontal surface, whether the vehicle 50 travels downhill, or whether the vehicle 50 travels uphill). is assumed to run at a constant speed).

Here, the road surface F1 coincides with the horizontal plane, and is inclined by an angle θ1 with respect to the imaging plane of the camera 30 (that is, the plane perpendicular to the imaging direction). Also, referring to FIG. 2, a vehicle 50 traveling on a road surface F2 is shown. The road surface F2 is a downward slope for the vehicle 50, and is inclined at an angle θ2 with respect to the imaging plane of the camera 30 (in this example, θ2<θ1). Further, referring to FIG. 3, road surface F3 is shown. The road surface F3 is an uphill slope for the vehicle 50, and is inclined at an angle θ3 with respect to the imaging plane of the camera 30 (in this example, θ3>θ1). Thus, the angle between the road surface and the imaging plane of the camera 30 can vary depending on the installation position of the camera 30 .

Furthermore, referring to FIG. 1, a movement vector V0 of the vehicle 50 in real space is shown. Furthermore, referring to FIG. 1, the vehicle length L0 of the vehicle 50 in real space is shown. However, since the road surface F1 is inclined at an angle θ1 with respect to the imaging plane of the camera 30, the length of the long side of the circumscribed rectangle K1 (FIG. 4) of the vehicle 50 projected onto the imaging plane of the camera 30 is L1. is different from the vehicle length L0 (L1<L0 in this example). A motion vector V1 projected onto the imaging surface of the camera 30 is different from the motion vector V0 (in this example, V1=V0·cos θ1).

Also, referring to FIG. 2, a movement vector V0 of the vehicle 50 in real space is shown. Furthermore, referring to FIG. 2, the vehicle length L0 of the vehicle 50 in real space is shown. However, since the road surface F2 is inclined at an angle θ2 with respect to the imaging plane of the camera 30, the length of the long side of the circumscribed rectangle K2 (FIG. 5) of the vehicle 50 projected onto the imaging plane of the camera 30 is L2. is different from both the vehicle length L0 and the long side length L1 (in this example, L1<L2<L0). A motion vector V2 projected onto the imaging surface of the camera 30 is different from the motion vector V0 (in this example, V2=V0·cos θ2).

Also, referring to FIG. 3, a movement vector V0 of the vehicle 50 in real space is shown. Furthermore, referring to FIG. 3, the vehicle length L0 of the vehicle 50 in real space is shown. However, since the road surface F3 is inclined at an angle θ3 with respect to the imaging plane of the camera 30, the length of the long side of the circumscribed rectangle K3 (FIG. 6) of the vehicle 50 projected onto the imaging plane of the camera 30 is L3. are different from the vehicle length L0, the long side length L1, and the long side length L2 (in this example, L3<L1<L2<L0). A motion vector V3 projected onto the imaging plane of the camera 30 is different from the motion vector V0 (in this example, V3=V0·cos θ3).

4 to 6 are diagrams showing examples of captured images captured by the camera 30. FIG. A captured image G1 shown in FIG. 4 is an image captured by the camera 30 of the vehicle 50 traveling on the road surface F1 (FIG. 1) that coincides with the horizontal plane. A vehicle 50 is shown in the captured image G1. However, as described above, since the road surface F1 is inclined by the angle θ1 with respect to the imaging surface of the camera 30, the length L1 of the long side of the circumscribed rectangle K1 of the vehicle 50 captured in the captured image G1 is equal to the vehicle length L0. are different (L1<L0 in this example). Also shown is the length B1 of the short side of the circumscribed rectangle K1 of the vehicle 50 captured in the captured image G1.

A captured image G2 shown in FIG. 5 is an image captured by the camera 30 of the vehicle 50 traveling on the downhill road surface F2 (FIG. 2). A vehicle 50 is shown in the captured image G2. However, as described above, since the road surface F2 is inclined by the angle θ2 with respect to the imaging surface of the camera 30, the length L2 of the long side of the circumscribed rectangle K2 of the vehicle 50 captured in the captured image G2 is equal to the vehicle length L0. are different (L1<L2<L0 in this example). Also, the short side length B2 of the circumscribing rectangle of the vehicle 50 captured in the captured image G2 substantially matches the short side length B1 (FIG. 4) of the circumscribing rectangle K1 of the vehicle 50 captured in the captured image G1.

A captured image G3 shown in FIG. 6 is an image captured by the camera 30 of the vehicle 50 traveling on the uphill road surface F3 (FIG. 3). A vehicle 50 is shown in the captured image G3. However, as described above, since the road surface F3 is inclined by the angle θ3 with respect to the imaging plane of the camera 30, the length L3 of the long side of the circumscribed rectangle K3 of the vehicle 50 captured in the captured image G3 is equal to the vehicle length L0. are different (L3<L1<L2<L0 in this example). In addition, the short side length B3 of the circumscribing rectangle K3 of the vehicle 50 captured in the captured image G3 substantially matches the short side length B1 (FIG. 4) of the circumscribing rectangle K1 of the vehicle 50 captured in the captured image G1. .

The outline of the road surface information measuring system 1 according to the embodiment of the present invention has been described above.

[1-2. Functional configuration example of road surface information measurement system]
Next, a functional configuration example of the road surface information measuring system 1 according to the embodiment of the present invention will be described. FIG. 7 is a block diagram showing the functional configuration of the road surface information measuring system 1 according to the embodiment of the invention. As shown in FIG. 7 , the road surface information measuring system 1 according to the embodiment of the invention includes a road surface information measuring device 10 and a camera 30 . The road surface information measuring device 10 includes a control section 110 , a communication section 130 and a storage section 150 .

Control unit 110 includes a CPU (Central Processing Unit) and the like, and its functions are realized by the CPU developing a program stored in a nonvolatile storage device in a RAM (Random Access Memory) and executing the program. obtain. At this time, a computer-readable recording medium recording the program may also be provided. Alternatively, control unit 110 may be composed of dedicated hardware, or may be composed of a combination of multiple pieces of hardware.

Control unit 110 includes data acquisition unit 111 , vehicle detection unit 112 , vehicle type determination unit 113 , road surface information acquisition unit 114 , movement vector calculation unit 115 , vehicle speed calculation unit 116 , and output unit 117 . Each block of control unit 110 will be described later in detail.

The communication unit 130 is configured by a communication interface, and communicates with the camera 30 via a communication cable. For example, the communication unit 130 sequentially receives a plurality of captured frames (moving image data) continuously captured in time series by the camera 30 . The communication unit 130 sequentially outputs the received multiple imaging frames to the data acquisition unit 111 .

Storage unit 150 is a storage device capable of storing programs and data for operating control unit 110 . In addition, the storage unit 150 can also temporarily store various data required during the operation of the control unit 110 . For example, the memory device may be a non-volatile memory device. The storage unit 150 also includes a vehicle information storage unit 151 and a processing result storage unit 152 . Each of these blocks in storage unit 150 will be described later in detail.

The vehicle information storage unit 151 stores vehicle information. Here, the vehicle information is information in which the vehicle type, the information regarding the length of the vehicle corresponding to the vehicle type, and the information regarding the road surface are associated with each other. In an embodiment of the invention, the information about the length of the vehicle is the ratio of the first length to the second length of the vehicle corresponding to the vehicle type (particularly the ratio of the first length to the second length). Mainly assume the case of including However, the information about the vehicle length is not limited to this. In particular, in the embodiment of the present invention, the first length is the length of the long side of the circumscribing rectangle of the vehicle captured in the captured image (capturing frame), and the second length is the length of the short side of the circumscribing rectangle. We mainly assume the case of length. However, the first length and the second length are not limited to this either.

Further, in the embodiments of the present invention, it is mainly assumed that the angle between the road surface and the imaging plane is included as an example of the information regarding the road surface. However, the information about the road surface is not limited to the angle between the road surface and the imaging plane.

FIG. 8 is a diagram showing an example of vehicle information. As shown in FIG. 8, the vehicle information includes the vehicle type, the ratio P of the length of the long side of the circumscribing rectangle to the length of the short side of the circumscribing rectangle captured in the captured image of the vehicle of the vehicle type, and the road surface and the captured image. The angles with respect to the plane are associated with each other.

Here, when the road surface on which the vehicle 50 travels is an uphill (that is, as shown in FIG. In the case where the ratio P is relatively small), the condition P<Pa is satisfied. At this time, the condition P<Pa may be associated with the angle θ3 (FIG. 3) between the road surface F3 and the imaging surface when the road surface on which the vehicle 50 travels is an uphill.

Similarly, when the road surface on which the vehicle 50 travels is a horizontal surface (that is, as shown in FIG. 4, the ratio of the long side length L1 of the circumscribing rectangle K1 to the short side length B1 P is moderate), the condition Pa≦P<Pb is satisfied. At this time, the condition Pa≦P<Pb may be associated with the angle θ1 (FIG. 1) between the road surface F1 and the imaging surface when the road surface on which the vehicle 50 travels is horizontal.

Further, when the road surface on which the vehicle 50 travels is a downhill (that is, as shown in FIG. P is relatively large), the condition Pb≦P is satisfied. At this time, the condition Pb≦P may be associated with the angle θ2 ( FIG. 2 ) between the road surface F2 and the imaging surface when the road surface on which the vehicle 50 travels is downhill.

In addition, in the embodiment of the present invention, three types of road surfaces, uphill, horizontal, and downhill, will be mainly described as examples. However, the method of dividing into three types is not limited to this example, and may be appropriately divided according to the angle between the road surface and the imaging surface. For example, the classification may be such that the first type is a steep uphill, the second type is a gentle uphill, horizontal and gentle downhill, and the third type is a steep downhill. Also, the number of road surface types may be two, or may be four or more. As the types of road surfaces increase, the detection accuracy of the angle between the road surface and the imaging surface improves.

Returning to FIG. 7, the description continues. The data acquisition unit 111 sequentially acquires, via the communication unit 130 , a plurality of captured frames continuously captured by the camera 30 . Then, the vehicle detection unit 112 attempts to detect a vehicle traveling on the road based on the captured image (captured frame). Here, vehicles may be detected in any way. For example, the vehicle may be an area identified from silhouettes extracted by differences between multiple captured frames. Alternatively, it may be a silhouette extracted from the difference between the background image and the captured image. Alternatively, the vehicle may be detected by a detector pre-built by machine learning. When the vehicle is detected by the vehicle detection unit 112, the vehicle detection unit 112 obtains a circumscribed rectangle of the vehicle in the captured image.

The vehicle type determination unit 113 determines the vehicle type detected by the vehicle detection unit 112 as the vehicle type. Here, the vehicle type may be discriminated in any way. As an example, the vehicle type determination unit 113 estimates the vehicle width, vehicle length, and vehicle height based on the vehicle detected by the vehicle detection unit 112, and based on the estimated vehicle width, vehicle length, and vehicle height, You can also identify the vehicle type. Alternatively, the vehicle type may be discriminated by a discriminator constructed in advance by machine learning.

The road surface information acquisition unit 114 calculates the length of the long side and the length of the short side of the circumscribing rectangle based on the circumscribing rectangle of the vehicle in the captured image obtained by the vehicle detection unit 112, and calculates the length of the short side of the circumscribing rectangle. Calculate the ratio of the length of the long side to the length. Then, the road surface information acquisition unit 114 calculates the ratio of the length of the long side to the length of the short side of the circumscribing rectangle, and the angle between the road surface and the imaging plane corresponding to the vehicle type identified by the vehicle type identification unit 113. is obtained from the vehicle information storage unit 151 (FIG. 8).

The motion vector calculation unit 115 calculates a motion vector of the vehicle based on a plurality of captured frames. Here, the motion vector may be calculated in any way. For example, the movement vector calculation unit 115 may calculate, as a movement vector, the difference between the positions of the same vehicle detected from each of the plurality of imaging frames by tracking the same vehicle between the plurality of imaging frames. . Alternatively, the motion vector calculation unit 115 may calculate, as a motion vector, the difference between the positions of the vehicle detected from each of a plurality of captured frames captured within a predetermined period of time.

The vehicle speed calculation unit 116 calculates the speed of the vehicle based on the movement vector calculated by the movement vector calculation unit 115 and the angle between the road surface and the imaging plane. For example, the vehicle speed calculation unit 116 calculates the movement vector of the vehicle in space by (V/cos θ), where V is the movement vector calculated by the movement vector calculation unit 115 and θ is the angle between the road surface and the imaging plane. can. Further, the vehicle speed calculation unit 116 can calculate a velocity vector by calculating a movement vector per unit time based on the movement vector of the vehicle in space, and can calculate the vehicle speed based on the magnitude of the velocity vector.

Output unit 117 outputs the vehicle speed calculated by vehicle speed calculation unit 116 . Here, the vehicle speed may be output anywhere. As an example, in the embodiment of the present invention, it is mainly assumed that the output unit 117 causes the processing result storage unit 152 to record the vehicle speed. However, the output unit 117 may output the vehicle speed to the display and display the vehicle speed on the display. Furthermore, the output unit 117 may record the angle between the road surface and the imaging plane acquired by the road surface information acquisition unit 114 in the processing result storage unit 152 (or may display it on the display).

The functional configuration example of the road surface information measuring system 1 according to the embodiment of the present invention has been described above.

<2. Hardware configuration example>
Next, a hardware configuration example of the road surface information measuring device 10 according to the embodiment of the present invention will be described. An example hardware configuration of the information processing device 900 will be described below as an example hardware configuration of the road surface information measuring device 10 according to the embodiment of the present invention. Note that the hardware configuration example of the information processing device 900 described below is merely an example of the hardware configuration of the road surface information measuring device 10 . Therefore, in the hardware configuration of the road surface information measuring device 10, unnecessary configurations may be deleted from the hardware configuration of the information processing device 900 described below, or new configurations may be added.

FIG. 9 is a diagram showing the hardware configuration of an information processing device 900 as an example of the road surface information measuring device 10 according to the embodiment of the present invention. The information processing device 900 includes a CPU (Central Processing Unit) 901, a ROM (Read Only Memory) 902, a RAM (Random Access Memory) 903, a host bus 904, a bridge 905, an external bus 906, and an interface 907. , an input device 908 , an output device 909 , a storage device 910 and a communication device 911 .

The CPU 901 functions as an arithmetic processing device and a control device, and controls general operations within the information processing device 900 according to various programs. Alternatively, the CPU 901 may be a microprocessor. The ROM 902 stores programs, calculation parameters, and the like used by the CPU 901 . The RAM 903 temporarily stores programs used in the execution of the CPU 901, parameters that change as appropriate during the execution, and the like. These are interconnected by a host bus 904 comprising a CPU bus or the like.

The host bus 904 is connected via a bridge 905 to an external bus 906 such as a PCI (Peripheral Component Interconnect/Interface) bus. Note that the host bus 904, the bridge 905 and the external bus 906 do not necessarily have to be configured separately, and these functions may be implemented in one bus.

The input device 908 includes input means for the user to input information, such as a mouse, keyboard, touch panel, button, microphone, switch, and lever, and an input control circuit that generates an input signal based on the user's input and outputs it to the CPU 901 . etc. A user who operates the information processing apparatus 900 can input various data to the information processing apparatus 900 and instruct processing operations by operating the input device 908 .

The output device 909 includes, for example, a CRT (Cathode Ray Tube) display device, a liquid crystal display (LCD) device, an OLED (Organic Light Emitting Diode) device, a display device such as a lamp, and an audio output device such as a speaker.

The storage device 910 is a device for data storage. The storage device 910 may include a storage medium, a recording device that records data on the storage medium, a reading device that reads data from the storage medium, a deletion device that deletes data recorded on the storage medium, and the like. The storage device 910 is configured by, for example, an HDD (Hard Disk Drive). The storage device 910 drives a hard disk and stores programs executed by the CPU 901 and various data.

The communication device 911 is, for example, a communication interface configured with a communication device or the like for connecting to a network. Also, the communication device 911 may support either wireless communication or wired communication.

The hardware configuration example of the road surface information measuring device 10 according to the embodiment of the present invention has been described above.

<3. Summary>
As described above, according to the embodiment of the present invention, the vehicle detection unit 112 detects a vehicle traveling on a road surface based on a captured image, the vehicle type determination unit 113 determines the vehicle type as a vehicle type, and the vehicle type and information about the length of the vehicle, a road surface information acquisition unit 114 that acquires information about the road surface, a motion vector calculation unit 115 that calculates the motion vector of the vehicle based on a plurality of imaging frames, and a motion vector and the road surface information. and a vehicle speed calculation unit 116 that calculates the speed of the vehicle based on the information.

According to this configuration, it is possible to calculate the vehicle speed without previously associating the distance in the real space with the distance in the image.

Although the preferred embodiments of the present invention have been described in detail above with reference to the accompanying drawings, the present invention is not limited to such examples. It is obvious that a person having ordinary knowledge in the technical field to which the present invention belongs can conceive of various modifications or modifications within the scope of the technical idea described in the claims. It is understood that these also naturally belong to the technical scope of the present invention.

For example, in the above description, the information about the length of the vehicle includes the ratio between the first length and the second length of the vehicle corresponding to the vehicle type. In the above description, the first length is the length of the long side of the circumscribing rectangle of the vehicle captured in the captured image, and the second length is the length of the short side of the circumscribing rectangle. assumed. However, the first length and the second length are not limited to this. The first length may be the horizontal length of the license plate in the captured image, and the second length may be the vertical length of the license plate.

That is, the vehicle detected by the vehicle detection unit 112 may not be the entire vehicle, but may be a license plate (that is, part of the vehicle). At this time, the circumscribing rectangle of the license plate is obtained by the vehicle detection unit 112 . Based on the size of the circumscribing rectangle (license plate size information), the vehicle type determination unit 113 may determine the type of license plate (large, medium plate, small plate) and store it in the vehicle type information storage unit 151 . Whether the vehicle detector 112 detects the entire vehicle or the license plate may be selected when the detector is trained. However, it is expected that the license plate detection rate will vary greatly depending on the angle at which the license plate is attached to the vehicle body. Therefore, the vehicle detection unit 112 may mainly detect the entire vehicle and correct the detection result of the entire vehicle based on the detection result of the license plate.

A case where the road surface information acquisition unit 114 obtains the angle between the imaging surface and the road surface has been mainly described above. However, it is assumed that the angle between the horizontal plane and the imaging plane is measured in advance when the camera 30 is installed. Therefore, the road surface information acquisition unit 114 may calculate the angle between the horizontal plane and the road surface based on the angle between the imaging plane and the road surface and the angle between the horizontal plane and the imaging plane measured in advance. Then, the output unit 117 may output the angle between the horizontal plane and the road surface. For example, the angle between the horizontal plane and the road surface can be used as the slope of the road surface in space.

The road surface information acquisition unit 114 can also calculate the direction of the road surface by the same method as the method for obtaining the angle between the imaging surface and the road surface. Furthermore, the road surface information acquisition unit 114 can also obtain information about unevenness of the road surface. For example, if there is a location where the vehicle speed is lower than the threshold value or a location where the movement vector suddenly changes, the road surface information acquisition unit 114 identifies the location as an abnormal location (for example, a depression or step). location, etc.).

Alternatively, the road surface information acquisition unit 114 may detect time-series changes in the road surface. For example, the road surface information acquisition unit 114 calculates the outer product of the past movement vector and the current movement vector data at the same location, and if the outer product is non-zero, there is some change in the road surface at that location (for example, the road surface distortion) is occurring.

1 road surface information measurement system 10 road surface information measurement device 110 control unit 111 data acquisition unit 112 vehicle detection unit 113 vehicle type determination unit 114 road surface information acquisition unit 115 movement vector calculation unit 116 vehicle speed calculation unit 117 output unit 130 communication unit 150 storage unit 151 vehicle Information storage unit 152 Processing result storage unit 30 Camera 50 Vehicle

Claims (7)

a vehicle detection unit that detects a vehicle traveling on a road surface based on the captured image;
a vehicle type determination unit that determines the type of the vehicle as a vehicle type;
a road surface information acquisition unit that acquires information about the road surface corresponding to the vehicle type and information about the length of the vehicle;
a motion vector calculation unit that calculates a motion vector of the vehicle based on a plurality of imaging frames;
a vehicle speed calculation unit that calculates the speed of the vehicle based on the movement vector and information about the road surface;
with
the information about the length of the vehicle is a ratio between a first length and a second length of the vehicle corresponding to the vehicle type;
The information about the road surface is an angle between the imaging plane of a camera that captures the captured image and the road surface,
Road surface information measuring device. The vehicle speed calculation unit
calculating a movement vector in space from the movement vector and the information about the road surface, calculating a movement vector per unit time from the movement vector in the space, and calculating the speed of the vehicle;
The road surface information measuring device according to claim 1. The first length is the length of the long side of the circumscribing rectangle of the vehicle in the captured image, and the second length is the length of the short side of the circumscribing rectangle.
The road surface information measuring device according to claim 1 or 2. The first length is the horizontal length of the license plate in the captured image, and the second length is the vertical length of the license plate.
The road surface information measuring device according to claim 1 or 2. The road surface information acquisition unit calculates the angle between the horizontal plane and the road surface based on the angle between the imaging plane and the road surface and the angle between the horizontal plane and the imaging plane measured in advance.
The road surface information measuring device according to claim 1 or 2 . Detecting a vehicle traveling on a road surface based on the captured image;
determining the type of the vehicle as a vehicle type;
obtaining information about the road surface corresponding to the vehicle type and information about the length of a predetermined portion of the vehicle;
calculating a movement vector of the vehicle based on a plurality of imaging frames;
calculating the speed of the vehicle based on the movement vector and information about the road surface;
including
the information about the length of the vehicle is a ratio between a first length and a second length of the vehicle corresponding to the vehicle type;
The information about the road surface is an angle between the imaging plane of a camera that captures the captured image and the road surface,
Road surface information measurement method. the computer,
a vehicle detection unit that detects a vehicle traveling on a road surface based on the captured image;
a vehicle type determination unit that determines the type of the vehicle as a vehicle type;
a road surface information acquisition unit that acquires information about the road surface corresponding to the vehicle type and information about the length of a predetermined portion of the vehicle;
a motion vector calculation unit that calculates a motion vector of the vehicle based on a plurality of imaging frames;
a vehicle speed calculation unit that calculates the speed of the vehicle based on the movement vector and information about the road surface;
with
the information about the length of the vehicle is a ratio between a first length and a second length of the vehicle corresponding to the vehicle type;
The information about the road surface is an angle between the imaging plane of a camera that captures the captured image and the road surface,
A program for functioning as a road surface information measuring device.

Images