JP2003217083A - Vehicle detecting method and device - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a vehicle detecting method for improving vehicle detecting accuracy. <P>SOLUTION: This device has (a) a step of storing vehicle shape template data for indicating a characteristic quantity of a contour line for indicating at least a part of a shape of a vehicle being a detecting object, (b) a step of storing non-vehicle shape template data for indicating the characteristic quantity of the contour line for indicating at least a part of a shape being not the detecting object, (c) a step of forming a binarized image for expressing a contour line of the traveling vehicle by imaging and binarizing an image of the traveling vehicle, (d) a step of extracting characteristic quantity data for indicating the characteristic quantity of the contour line of the binarized image, and (e) a step of determining that the detecting object is included in the binarized image on the basis of a comparing result by comparing the respective vehicle shape template data and non-vehicle shape template data with the characteristic quantity data. <P>COPYRIGHT: (C)2003,JPO

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a vehicle detection method and apparatus capable of accurately recognizing a running vehicle and accurately detecting its position.

[0002]

2. Description of the Related Art It is necessary to identify a moving vehicle and identify its position, for example, in order to identify a vehicle that violates the speed limit or a vehicle loaded with dangerous goods whose entry into a long tunnel is prohibited. Is. That is, in order to identify these vehicles, the vehicle number on the license plate of these speeding vehicles and the letters on the plate such as "danger,""poison," and "play" posted on vehicles carrying dangerous goods are used. It is necessary to accurately detect the position that can be accurately read, but in order to do so, first the vehicle itself is accurately detected, and the position of the vehicle on the road is detected, and It is necessary to accurately predict the timing at which the plate that indicates that there is is readable.

In vehicle detection processing by moving image processing to which pattern recognition technology is applied, a large number of vehicle shape patterns to be detected are registered, and whether or not the vehicle is a vehicle is determined based on the degree of similarity with the registered patterns.

[0004]

However, in the moving image processing to which the above-mentioned pattern recognition technique is applied, an object other than the vehicle which is very similar to the vehicle shape may be erroneously detected as the vehicle.

In the present invention, it is an object of the present invention to provide a vehicle detection method and apparatus capable of suppressing erroneous detection of an object which has been erroneously detected as a vehicle and improving vehicle detection accuracy. .

Japanese Patent No. 2893814 discloses that
The following plate cutting device in the vehicle number automatic reading device is disclosed. That is, in a vehicle number automatic reading device for automatically identifying the plate number of a vehicle running or stopped on the road, a photographing means for photographing the road and a plate frame candidate determining means for judging a plate frame candidate from the photographed image. A character area candidate determination means for determining a character area candidate from a captured image; a portion surrounded by a plate frame estimated based on the plate frame candidate; and a character area estimated based on the character area candidate. And a plate position determining means for determining the plate position on the basis of the degree of overlap.

[0007]

A vehicle detection method according to the present invention comprises: (a) storing vehicle shape template data indicating a feature amount of a contour line showing at least a part of the shape of a vehicle to be detected; (B) storing non-vehicle shape template data indicating a feature amount of a contour line that indicates at least a part of the shape that is not the detection target;
(C) capturing an image of the traveling vehicle and binarizing the image to generate a binarized image in which a contour line of the traveling vehicle is represented; and (d) a feature amount of the contour line of the binarized image. And (e) comparing each of the vehicle shape template data and the non-vehicle shape template data with the feature amount data, and binarizing based on the result of the comparison. Determining that the image includes the detection target.

In the vehicle detection method of the present invention, in the case (e), as a result of the comparison, it is determined that the feature amount data is more similar to the non-vehicle shape template data than the vehicle shape template data. Determines that the detection target does not exist in the feature amount data.

In the vehicle detection method of the present invention, the vehicle shape template data is data of an area including a license plate portion of the vehicle, and the non-vehicle shape template data does not include the license plate portion of the vehicle. This is the area data.

In the vehicle detection method of the present invention, the feature amount of the contour line is represented by a vector amount of the direction and size of the contour line.

In the vehicle detection method of the present invention, at least one of the vehicle shape template data and the non-vehicle shape template data is at least a vehicle shape obtained by executing the vehicle detection method at a plurality of locations. The feature amount of the contour line showing a part is stored.

In the vehicle detection method of the present invention, the feature amount data indicates a feature amount of the contour line included in a partial area of the cut out binarized image.

The vehicle detection device of the present invention includes a first storage unit for storing vehicle shape template data indicating a feature amount of a contour line showing at least a part of a shape of a vehicle to be detected, and a shape not to be detected. A second storage unit that stores non-vehicle shape template data indicating a feature amount of a contour line indicating at least a part of the above, and a binary value in which the contour line of the traveling vehicle is represented by binarizing an image of the traveling vehicle. A binarized image generation unit that generates a digitized image, a feature amount extraction unit that extracts feature amount data indicating a feature amount of the contour of the binarized image, the vehicle shape template data, and the non-vehicle shape template A determination unit that compares each of the data and the feature amount data and determines that the binary image includes the detection target based on the result of the comparison.

[0014]

BEST MODE FOR CARRYING OUT THE INVENTION An embodiment of a vehicle detection method of the present invention will be described with reference to the accompanying drawings.

FIG. 1 is a schematic block diagram of an apparatus showing this embodiment, FIGS. 2 and 3 are flow charts of a vehicle detection method of this embodiment, and FIG. 4 is a pattern feature amount on a screen imaged by an imaging device. FIG. 5 is a diagram for explaining a rectangular area used for calculation, and FIG. 5 is an explanatory diagram when a vehicle is detected. Figure 6
Is a vehicle shape template storage device 14 that stores a vehicle pattern to be detected, and a non-vehicle shape template storage device 15 that stores a non-vehicle pattern that is similar to the vehicle pattern to be detected and that is likely to be erroneously detected. It is a figure. FIG. 7 is a diagram for explaining the determination of the degree of similarity during the vehicle detection process.

In FIG. 1, reference numeral 1 is a road, 2 is a passing vehicle, 3 is a gantry for installing a light source 5 such as a stroboscope for illuminating the vehicle on the road, 4 is an image pickup device for vehicle detection, and 6
Is a position on the road 1 that is optimal for capturing an image of the license plate of the vehicle 2.

Further, reference numeral 7 is an analog / digital conversion circuit for analog / digital converting the signal from the image pickup device 4, reference numeral 8 is a data smoothing circuit for removing noise,
Reference numeral 9 is an edge enhancement circuit that enhances the edges of the image by subjecting the input image to differential processing using a Sobel differential filter or the like, and reference numeral 10 is a binarization / storage circuit that binarizes and stores the enhanced image.

Further, reference numeral 11 refers to how much and in what direction the contour line of the binarized image has components, that is, how many horizontal components, vertical components and 45 ° components, respectively. , A pattern feature quantity extraction circuit that extracts a pattern feature quantity by expressing it with a vector quantity of the direction and size of the contour line.

Further, reference numeral 12 compares the vehicle shape template of the front shape of the vehicle stored in the vehicle shape template storage device 14 with the pattern feature quantity extracted by the pattern feature quantity extraction circuit 11 to determine the similarity between the two. This is a comparison / collation circuit for calculating.

Reference numeral 13 is a threshold value for checking whether the similarity of the pattern feature quantity calculated by the comparison / collation circuit 12 is equal to or more than a certain threshold value.

Further, reference numeral 14 expresses a contour line direction pattern feature amount in the front surface shape of the vehicle to be detected by a vector amount of the direction and size of the contour line, stores a certain number of vehicle types as a template, and other than that. It is a vehicle shape template storage device that statistically processes and deforms a pattern by a known method to process it so that pattern matching can be performed.

Reference numeral 15 indicates the contour direction pattern feature amount in a shape similar to the front shape of the vehicle to be detected, which is stored in the vehicle shape template storage device 14 and may be erroneously detected. A non-vehicle shape that is stored as a template and stores a certain number of vehicle types as a template, and other patterns are statistically processed by a known method, deformed, and processed for pattern matching. It is a template storage device.

In the non-vehicle shape template storage device 15, the shape pattern of an object similar to the vehicle shape is registered as a "non-vehicle" shape pattern, and such a vehicle that should be detected and an object that is likely to make an error are detected. The similarity with the "non-vehicle" is set to be higher than the similarity with the power "vehicle".

As shown in FIG. 6, if the "vehicle shape to be detected" stored in the vehicle shape template storage device 14 is the area 14a including the license plate portion of the vehicle, the shape pattern is similar to that of the area 14a. Therefore, it is apt to be erroneously detected that the area 1 other than the area 14a of the vehicle front shape is
5a. The region 15a has a somewhat complicated shape such as a front grill of a large vehicle. Other examples of the area 15a include a windshield, a speed indicator light of a large vehicle, a cargo, a ceiling portion, and the like.

Further, reference numeral 16 indicates that when a vehicle is detected, the vehicle is license plate, "danger", "poison",
A signal is sent to the light source light emission control device 17 that controls the light source 5 such as a strobe to emit light when the optimum timing (position) for reading a plate such as "play" is reached, and the signal is obtained. It is a character recognition control circuit that performs control to receive image pickup data from the binarization / storage device 10.

In the present embodiment, for example, a plurality of image pickup devices 4 and a light source 5 such as a strobe are installed on a gantry 3 provided across the road 1, and the plurality of image pickup devices 4 cover the entire width of the road 1. A vehicle traveling at any position on the road 1 can be captured by capturing an image.

When the vehicle 2 is detected by the vehicle detection device of this embodiment, the vehicle 2 picks up an image pickup position 6 on the road 1 (the image pickup position 6 in the figure is a temporary frame shown for convenience of explanation. ), The light source 5 such as a strobe is turned on to recognize the characters on the license plate of the vehicle 2 or on the plates such as "danger,""poison," and "drama" posted on vehicles carrying dangerous goods. Recognize the character.

The image pickup device 4 and the light source 5 such as a strobe
Was installed on the gantry 3, but it is obvious that this may be installed on a pillar standing on the roadside.

The image pickup device 4 detects the vehicle 2 on the road 1 by continuously picking up the image of the road 1. The detection is performed by the vehicle indicated by the thick line in the picked-up image 30 (one frame) shown in FIG. A rectangular area 32 for pattern feature calculation, which is large enough to cover the front surface of the vehicle represented by a plurality of squares in the detection target area 31, is cut out, and the image data therein is stored in the vehicle shape template storage device 14. The comparison is made with the front pattern template of the vehicle, and also with the non-vehicle pattern template stored in the non-vehicle shape template storage device 15. Pattern matching between the image data captured by the image capturing device 4 and each of the front pattern template of the vehicle shape template storage device 14 and the non-vehicle pattern template of the non-vehicle shape template storage device 15 may be performed by a known method. it can. In this case, for example, a template matching method using Mahalanobis distance can be used.

The cutout of the pattern characteristic amount calculation rectangular area 32 is performed by cutting the pattern characteristic amount calculation rectangular area 32 in the vehicle detection target area 31 in the horizontal (X) direction 33 and the vertical (y) direction.
The vehicle is detected in each of the cut out regions by moving one unit in the direction 34, for example, to the position indicated by (n, m).

As shown in FIG. 7, when the pattern feature amount calculation rectangular area 32 is the windshield portion 32a, the pattern feature amount calculation rectangular area 32 is formed.
Is determined to have a higher degree of similarity to the non-vehicle pattern template of the non-vehicle shape template storage device 15 than the front surface pattern template of the vehicle shape template storage device 14. As a result, it is determined that the rectangular area 32 for calculating the pattern feature quantity 32a is not the target to be detected. On the other hand, the pattern feature amount calculation rectangular area 32 includes an area 14a including a license plate portion 32b.
(See FIG. 6), the pattern feature amount calculation rectangular area 32 is determined as the non-vehicle shape template storage device 1
It is determined that the degree of similarity with the front surface pattern template of the vehicle shape template storage device 14 is higher than that of the non-vehicle pattern template of No. 5. As a result, the rectangular area 32 for calculating the pattern feature quantity 32b is determined to be the target to be detected.

That is, the rectangular area 32 for pattern feature quantity calculation
By evaluating whether the vehicle is more similar to “vehicle” or “non-vehicle”, it becomes possible to accurately detect only the vehicle front portion including only the license plate portion.

Then, this operation is repeated for each frame of the image pickup screen, and when the vehicle 2 is captured at the position of the pattern feature amount calculation rectangular area 32 shown in FIG. 5, for example, vehicle detection is performed at that position. Is determined as.

This determination method will be described with reference to the flow charts shown in FIGS. 2 and 3 and the block diagram of the vehicle detection device of the present embodiment shown in FIG. 2 and 3 are
The two are linked at the position of the chain double-dashed line.

First, in step S21, the pattern feature amount calculation rectangular area 32 is set to the origin position (n = 0, m = 0) in the vehicle detection target area 31, so that x = 0 and y = 0.

Next, as shown in step S22, one frame 30 of the image pickup screen from the image pickup device 4 is read, analog / digital conversion is performed by the analog / digital conversion circuit 7, and then smoothing is performed as shown in step S23. The noise component is removed by the smoothing circuit 8 by a known smoothing method.

Next, as shown in step S24, the image in the vehicle detection target area 31 of the image pickup screen (one frame) 30 is edge-enhanced by the edge emphasizing circuit 9 using a known Sobel differential filter or the like. Further, as shown in step S25, the edge-enhanced image is binarized by the binarization / storage circuit 10 and stored. The edge emphasizing circuit 9 extracts only the contour of the vehicle by performing two-dimensional differentiation on the image in which the vehicle or the like is shown. The binarization / storage circuit 10 further binarizes the contour of the vehicle.

In the next step S26, the rectangular area 32 for calculating the pattern feature quantity is cut out at the origin position of the vehicle detection target area 31 of FIG. 4 in which the vehicle candidate is detected. next,
In step S27, the pattern feature amount extraction circuit 11 extracts the feature amount of the pattern in the pattern feature amount calculation rectangular area 32. This is to check in which direction and to what extent each of the contour lines of the pattern in which the edges in the pattern feature amount calculation rectangular area 32 are emphasized, that is, to see the vector amount of the direction and size of the contour line. Pattern feature amount is calculated by using, for example, the horizontal component of the contour line,
The magnitudes of the vertical direction component and the 45 ° direction component are calculated to obtain pattern feature amount data.

After the pattern feature amount data in the first rectangular region 32 for pattern feature amount calculation is extracted in step S27, as shown in step S28,
The matching circuit 12 uses the extracted pattern feature amount data, the vehicle shape template of the vehicle front shape stored in the vehicle shape template storage device 14, and the non-vehicle pattern template stored in the non-vehicle shape template storage device 15. It compares and collates, calculates the degree of similarity, and stores it. Since this similarity calculation is a value represented by a vector quantity indicating in which direction and in what extent the pattern feature amount data is present as described above, the front surface of the vehicle stored in the vehicle shape template storage device 14 is calculated. It can be easily calculated by comparing with the value indicating the vector amount of the contour line in the non-vehicle pattern template stored in the vehicle shape template of the shape and the non-vehicle shape template storage device 15. Moreover, since the pattern feature amount data is a value indicating the vector amount of the contour line, the similarity can be calculated regardless of the size of the captured image.

In step S28, it is determined that the pattern feature amount calculation rectangular area 32 has a higher degree of similarity with the non-vehicle pattern template of the non-vehicle shape template storage device 15 than the front surface pattern template of the vehicle shape template storage device 14. If so, the degree of similarity (the calculated value in step S28) of the pattern feature amount calculation rectangular area 32 with the front surface pattern template of the vehicle shape template storage device 14 is set to 0 or a negative value, which will be described later. In step S34, the area is prevented from being selected.

In this way, when the similarity between the pattern feature amount data in the first pattern feature amount calculating rectangular area 32 and the vehicle shape template is calculated and stored, the pattern feature amount of the next pattern feature amount calculating rectangular area 32 is stored. In order to calculate, the pattern feature amount calculation rectangular area 32 is moved by x + in one step in the x direction in step S29.
1 is calculated, and it is determined in step S30 whether the value of x does not exceed the final position coordinate n of the vehicle detection target area 31. In this case, since x is 2, the processing is step S26.
Returning to step S27, the process from step S27 to step S29 described above is repeated. If the value of x exceeds n in step S30, the process goes to step S31.

Then, in step S31, x is set to 0, and in step S32, y + 1 is calculated in order to move the rectangular region 32 for pattern feature quantity calculation in the y direction by one box, and the value of y is calculated in step S33. It is determined whether the vehicle candidate does not exceed the final position coordinate m of the vehicle detection target area 31 in which the vehicle candidate is detected. In this case, y is 2, so the process returns to step S26, and step S27 described above is executed.
The processing from step S32 is repeated from step S3
When the value of y exceeds m in 3, the process goes to step S34.

Then, in this step S34, the pattern feature amount calculation rectangular area 32 showing the highest similarity between the pattern feature amount data stored in the comparison / collation circuit 12 and the vehicle shape template is selected, and step S34 is selected. This similarity is compared with the threshold 13 in S35.
As a result, when the similarity is higher than the threshold 13, it is determined that the vehicle 2 exists in the pattern feature amount calculation rectangular area 32, a vehicle detection flag is set in step S36, and the vehicle detection result is character recognition control in step S37. It is sent to the circuit 16. When the data for one frame is processed in this manner, the process returns to the first step S21, and the vehicle detection operation described above is repeated.

On the other hand, the character recognition control circuit 16 to which the vehicle detection result is sent receives the pattern feature amount calculation rectangular area in which the vehicle 2 exists in the vehicle detection target area 31 stored in the binarization / storage circuit 10. 32, the size of the vehicle 2 is determined to determine whether it is the optimum timing (position) for reading a license plate or a plate such as “danger,” “poison,” or “play”. If it is determined that the characters are too small in the reading of the plate at this position, the size of the vehicle 2 and the position where the vehicle 2 is detected in the next frame or in the next frame, and the size of the vehicle 2 in the previous frame. The speed of the vehicle 2 is calculated according to the change from the position or size of the vehicle 2, and the license plate or "danger",
The optimum timing (position) for reading a plate such as "poison" or "drama" is calculated, and a signal is sent to the light source emission control circuit 17.

Therefore, the light source light emission control device 17 is provided in the vehicle 2
The light source 5 such as a strobe light is emitted at the optimum timing (position) to read the license plate of "No", "dangerous", "poison", "drama", etc. Smoothing circuit 8 through 7
After being smoothed by, the character plate is sent to the character recognition control circuit 16 and the character recognition circuit (not shown) recognizes the license plate of the vehicle 2 and characters such as “danger”, “poison”, and “play”.

By registering the non-vehicle pattern other than the vehicle pattern to be detected in this way, an object that has been erroneously detected as a vehicle can be prevented from being erroneously detected, so that the vehicle detection accuracy is improved. Can be achieved.

In the above embodiment, the vehicle shape template 14a of the vehicle front shape stored in the vehicle shape template storage device 14 and the non-vehicle pattern template 15a stored in the non-vehicle shape template storage device 15 are respectively stored in the book. In addition to the vehicle shape template and the non-vehicle shape template registered in the vehicle shape template storage device 14 and the non-vehicle shape template storage device 15 at the time of installation of the vehicle detection device of the embodiment, the vehicle shape pattern detected after installation The non-vehicle shape template can be automatically registered at any time. This improves the detection accuracy.

Further, the vehicle detection device of this embodiment is installed at a large number of points, and the devices installed at the large number of points are connected to each other by a network. The detection accuracy is improved by mutually reflecting the vehicle shape templates and automatically registering them in each device as needed. In this case, the vehicle shape pattern and non-vehicle shape template obtained by each device are
Data is processed and managed collectively by the host computer, and the host computer can send the data to each device.

Further, according to this embodiment, the vehicle 2 can be operated by the single image pickup device 4 without separately providing a vehicle position detecting device using a laser, an ultrasonic wave, a loop coil or the like.
Timing (position) for recognizing information, reading license plates and plates such as "danger,""poison," and "play"
And calculation of image data for recognizing these characters can be performed. Moreover, the recognition of the vehicle is
By using the contour direction pattern feature amount, it can be performed even if the vehicle is far away, and the shadow of the vehicle itself and the shadow of the building are not mistaken for the vehicle, and the license plate of the vehicle and the " A vehicle detection method and device optimal for recognizing characters such as "danger", "poison", and "play" can be provided.

In the above description, the analog / digital conversion circuit 7, the smoothing circuit 8, the edge emphasizing circuit 9, the binarization / storage circuit 10, for processing the signal from the image pickup device 4,
Pattern feature quantity extraction circuit 11, comparison / collation circuit 12, threshold value 13, vehicle shape template storage device 14, non-vehicle shape template storage device 15, character recognition control circuit 16,
Although it has been described that the light source emission control device 17 is used,
It goes without saying that circuits other than the analog / digital conversion circuit 7 may be configured using a computer and its storage device.

[0051]

According to the vehicle detection method of the present invention, vehicle detection accuracy is improved.

[Brief description of drawings]

FIG. 1 is a schematic block diagram of an apparatus showing an embodiment of a vehicle detection method of the present invention.

FIG. 2 is a flowchart showing a part of the vehicle detection method of the present embodiment.

FIG. 3 is a flowchart showing another part of the vehicle detection method of the present embodiment.

FIG. 4 is a diagram for explaining a rectangular area used for pattern feature amount calculation on a screen imaged by an imaging device in the present embodiment.

FIG. 5 is an explanatory diagram when a vehicle is detected in the present embodiment.

FIG. 6 shows a vehicle shape template storage device that stores a vehicle pattern to be detected and a non-vehicle shape template storage device that stores a non-vehicle pattern that is similar to the vehicle pattern to be detected and that is likely to be erroneously detected. It is a figure for explaining.

FIG. 7 is a diagram for explaining determination of similarity during vehicle detection processing.

[Explanation of symbols]

1 road 2 passing vehicles 3 gantry 4 Vehicle detection imaging device 5 light sources 6 Imaging position on the road 7 Analog / digital conversion circuit 8 Smoothing circuit 9 Edge enhancement circuit 10 Binarization / memory circuit 11 Pattern feature extraction circuit 12 Comparison / collation circuit 13 threshold 14 Vehicle shape template storage device 15 Non-vehicle shape template storage device 16 character recognition control circuit 17 Light source emission control device

   ─────────────────────────────────────────────────── ─── Continued front page    (72) Inventor Jun Kuroda             2-1-1 Niihama, Arai-cho, Takasago, Hyogo Prefecture             Takasago Laboratory, Mitsubishi Heavy Industries, Ltd. F-term (reference) 5B057 AA16 CA02 CA08 CA12 CA16                       CB02 CB06 CB12 CB16 CE02                       CE03 CE12 DA08 DA12 DB02                       DB09 DC09 DC16 DC34                 5C054 CB03 DA09 FC05 FC12 FC14                       FC16 GB13 HA26                 5H180 AA01 CC04 DD02                 5L096 AA06 BA04 CA02 EA05 EA43                       FA06 FA34 HA09 JA03 JA09

Claims (7)

[Claims] 1. A step of storing (a) vehicle shape template data indicating a feature amount of a contour line showing at least a part of a shape of a vehicle to be detected, and (b) at least one of shapes not to be detected. A step of storing non-vehicle shape template data indicating a feature amount of a contour line indicating a part, and (c) an image of a traveling vehicle is captured and binarized to obtain a binarized image representing the contour line of the traveling vehicle. (E) a step of generating, (d) a step of extracting characteristic amount data indicating a characteristic amount of the contour line of the binarized image, and (e)
Comparing each of the vehicle shape template data and the non-vehicle shape template data with the feature amount data, and determining that the binary image includes the detection target based on a result of the comparison. Vehicle detection method comprising. 2. The vehicle detection method according to claim 1, wherein in (e), as a result of the comparison, the feature amount data is more similar to the non-vehicle shape template data than the vehicle shape template data. If so, the vehicle detection method determines that the detection target does not exist in the feature amount data. 3. The vehicle detection method according to claim 1, wherein the vehicle shape template data is data of an area including a license plate portion of a vehicle, and the non-vehicle shape template data is a vehicle shape. A vehicle detection method which is data of an area not including the license plate portion. 4. The vehicle detection method according to any one of claims 1 to 3, wherein the feature amount of the contour line is represented by a vector amount of the direction and size of the contour line. 5. The vehicle detection method according to any one of claims 1 to 4, wherein at least one of the vehicle shape template data and the non-vehicle shape template data is a plurality of locations in the vehicle detection method. The vehicle detection method in which the feature amount of the contour line indicating at least a part of the shape of the vehicle obtained by the execution in step 1 is stored. 6. The vehicle detection method according to claim 1, wherein the feature amount data is a feature of the contour line included in a partial region of the cut out binarized image. Vehicle detection method that indicates quantity. 7. A first storage unit that stores vehicle shape template data indicating a feature amount of a contour line that indicates at least a part of the shape of a vehicle that is a detection target, and at least a part of the shape that is not the detection target. A second storage unit that stores non-vehicle shape template data indicating a feature amount of a contour line, and an image of a traveling vehicle is captured and binarized to generate a binarized image in which the contour line of the traveling vehicle is represented. 2 A binarized image generation unit; a feature amount extraction unit that extracts feature amount data indicating a feature amount of the contour of the binarized image; the vehicle shape template data and the non-vehicle shape template data; A vehicle detection device, comprising: a determination unit that compares the feature amount data and determines that the binary image includes the detection target based on a result of the comparison.