Bicycle parking management system

Abstract

This invention provides a motorcycle identification system and parking management system that can subdivide and identify different types of motorcycles. [Solution] The motorcycle identification system 20 includes a first camera 212 for acquiring a first image which is an image of the side of the motorcycle 12a, a second camera 214 for acquiring a second image which is an image of the motorcycle's license plate, and an identification device 220 for identifying at least the legally defined classification of the motorcycle 12a based on the first and second images.

Description

Technical Field

[0001] The present invention relates to a parking lot management system.

Background Art

[0002] Patent Document 1 discloses a vehicle type discrimination device that can be easily installed and can easily discriminate the vehicle type. This vehicle type discrimination device includes a temperature detection means for detecting the temperature at a predetermined position of the vehicle, and a discrimination means for discriminating the vehicle type of the vehicle based on the temperature detected by the temperature detection means.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] An object of the present invention is to provide a parking lot management system that can classify and identify the types of two-wheeled vehicles.

Means for Solving the Problems

[0005] The invention described in claim 1 comprises a first camera for acquiring a first image which is an image of the side of a two-wheeled vehicle; a second camera for acquiring a second image which is an image of the license plate of the two-wheeled vehicle; an identification device having a vehicle type identification unit that identifies at least whether the type of the two-wheeled vehicle is a bicycle, a motorcycle, or a kick scooter from the first image; a plate identification unit that identifies the type of the license plate from the second image; and an identification unit that identifies the classification of the two-wheeled vehicle based on a combination of the type of the two-wheeled vehicle identified by the vehicle type identification unit and the type of the license plate identified by the plate identification unit, wherein the vehicle type identification unit detects the two-wheeled vehicle based on the first image using a first machine learning model used for object detection. The parking lot management system includes: a primary vehicle processing unit that outputs information about a region A where the detected motorcycle is located; a secondary vehicle processing unit that identifies the type of motorcycle using a second machine learning model used for category classification based on an image cropped from the first image to include region A; and a plate identification unit that detects the license plate using a third machine learning model used for object detection based on the second image and outputs information about a region B where the detected license plate is located; and a secondary plate processing unit that identifies the type of license plate using a fourth machine learning model used for category classification based on an image cropped from the second image to include region B.

[0006] The invention described in claim 2 is a bicycle parking management system described in claim 1, before The first machine learning model identifies the type of motorcycle that was detected. do .

[0007] The invention described in claim 3 is a bicycle parking management system described in claim 2, wherein if the primary vehicle processing unit is unable to detect the motorcycle, it determines that there is no motorcycle present.

[0008] The invention described in claim 4 relates to the bicycle parking management system described in any one of claims 1 to 3, wherein the identification device identifies classification It is further equipped with an admission ticket machine that issues admission tickets with the following printed on them. [Effects of the Invention]

[0009] According to the present invention, it is possible to provide a parking lot management system that can subdivide and identify different types of motorcycles. [Brief explanation of the drawing]

[0010] [Figure 1] This is a classification of two-wheeled vehicles that can be identified by a bicycle parking management system according to one embodiment of the present invention. [Figure 2] This is an explanatory diagram showing the external appearance of a part of the bicycle parking management system. [Figure 3] This is a plan view corresponding to Figure 2. [Figure 4] This is a plan view corresponding to Figure 2, where the two-wheeled vehicle is a Class 1 moped. [Figure 5] This is a block diagram showing the configuration of the bicycle parking management system. [Modes for carrying out the invention]

[0011] Next, embodiments of the present invention will be described with reference to the attached drawings to facilitate understanding of the invention. Note that parts not relevant to the description may be omitted from the illustrations.

[0012] A bicycle parking management system 10 according to one embodiment of the present invention can set parking fees according to the classification of a two-wheeled vehicle, which is identified by a combination of the type of two-wheeled vehicle and the type of license plate. The classifications that can be identified include at least the classifications legally defined by the Road Transport Vehicle Act, etc., and for example, as shown in Figure 1, they are 1) bicycles, 2) Class 1 mopeds, 3) Class 2 mopeds, 4) small two-wheeled vehicles, 5) specified small mopeds, 6) kick scooters (those without a motor), and 7) light two-wheeled vehicles.

[0013] Note that "White (Small)" and "White (Large)" in Figure 1 refer to the smaller and larger white license plates, respectively. "Yellow" refers to a yellow license plate. "Pink" refers to a pink license plate. "White + Green Border" refers to a license plate with a green border on a white background. "New License Plate" refers to the license plate that is 10 centimeters in both length and width and is intended for use on certain small mopeds. Furthermore, the reason for classifying motorcycles without license plates as bicycles is that it is not possible to distinguish between motorcycles and bicycles with sufficient accuracy. By classifying them as bicycles, parking fees can be set lower, thereby reducing complaints from users.

[0014] The classifications are not limited to those shown in Figure 1; for example, mini-car registered vehicles with light blue license plates may be added as one of the classifications. Furthermore, the bicycle parking management system 10 is a system for subdividing and identifying the types of two-wheeled vehicles as needed, and is not for identifying them according to legally defined classifications.

[0015] As shown in Figures 2 to 5, the bicycle parking management system 10 includes a motorcycle identification system 20, an entrance reception machine 50, and a flap-type gate 60.

[0016] As shown in Figures 2 and 5, the motorcycle identification system 20 has a side camera 212, a rear camera 214, and an identification device 220, and can identify the aforementioned motorcycle classifications, such as the bicycle 12a shown in Figure 3 and the Class 1 moped 12b shown in Figure 4.

[0017] The side camera (an example of the first camera) 212 is a camera for acquiring an image of the side of the vehicle body (an example of the first image), and is arranged, for example, at a height position of 2,000 to 2,500 mm. The reason for setting the lower limit of the height position of the side camera 212 is that since the side camera 212 is arranged at a position where a child's hand cannot reach, the possibility of being tampered with is reduced. The reason for setting the upper limit of the height position is that since the side camera 212 is arranged at a position where an image capturing the characteristics of a two-wheeled vehicle can be obtained, the type of the two-wheeled vehicle can be specified with higher accuracy.

[0018] The rear camera (an example of the second camera) 214 is a camera for acquiring an image of the number plate provided at the rear of the vehicle body (an example of the second image). When there are restrictions on setting the route of the two-wheeled vehicle entering from the roadway, the rear camera 214 does not necessarily have to be provided on the rear side of the vehicle body. For example, the rear camera 214 may be provided at the upper part in front of the vehicle body, and may image the number plate image through a mirror installed on the rear side of the vehicle body.

[0019] The identification device 220 can identify at least the legally defined classification of the two-wheeled vehicle based on the side image of the two-wheeled vehicle captured by the side camera 212 and the number plate image captured by the rear camera 214. The identification device 220 includes a vehicle type identification unit 222, a plate identification unit 224, and an identification unit 226.

[0020] The vehicle type identification unit 222 is composed of a primary vehicle type processing unit 222a and a secondary vehicle type processing unit 222b, and can at least identify which of a bicycle, a motorcycle, and a kick scooter the type of the two-wheeled vehicle is from the side image of the two-wheeled vehicle captured by the side camera 212.

[0021] The primary vehicle type processing unit 222a detects the two-wheeled vehicle by a first machine learning model learned to be able to detect the two-wheeled vehicle based on the side image of the two-wheeled vehicle, specifies the type of the detected two-wheeled vehicle, and can output the position information of the area A where the two-wheeled vehicle is located. Furthermore, the primary vehicle processing unit 222a can determine which vehicle to identify when the image acquired by the side camera 212 includes multiple motorcycles. The first machine learning model is one used for object detection.

[0022] The secondary vehicle processing unit 222b can identify and classify the type of motorcycle based on a cropped image extracted from a side view image of the motorcycle to include region A, using a second machine learning model that has been trained to classify motorcycles. The second machine learning model is one used for categorical classification. The second machine learning model identifies the type of motorcycle based on region A where motorcycles already exist, thus improving the accuracy of the identification results.

[0023] The plate identification unit 224 consists of a primary plate processing unit 224a and a secondary plate processing unit 224b, and can identify the type of license plate from the image of the license plate captured by the rear camera 214. It should be added that the plate identification unit 224 does not read the characters on the license plate.

[0024] The primary plate processing unit 224a can detect license plates based on images of license plates using a third machine learning model that has been trained to detect license plates, and output information about the location of the detected license plate in region B. The third type of machine learning model is one used for object detection.

[0025] The secondary plate processing unit 224b can identify and classify the type of license plate based on a cropped image that includes region B, obtained from the license plate image, using a fourth machine learning model that has been trained to classify license plates. Furthermore, the secondary plate processing unit 224b can correct false detections by the primary plate processing unit 224a and classify the vehicle as having no license plate. The fourth type of machine learning model is one used for categorical classification. The fourth machine learning model improves the accuracy of the identification results because it identifies the type of license plate based on region B where the license plate already exists.

[0026] The identification unit 226 can identify whether the motorcycle is classified as 1) bicycle, 2) moped (50cc class), 3) moped (50cc class), 4) small motorcycle, 5) specific small motorcycle, 6) kick scooter, or 7) light motorcycle, based on the type of motorcycle identified by the vehicle type identification unit 222 and the type of license plate identified by the license plate identification unit 224.

[0027] Specifically, the identification unit 226 identifies the classification according to the matrix shown in Figure 1. For example, if the vehicle type identification unit 222 identifies a two-wheeled vehicle as a bicycle, and the license plate identification unit 224 identifies the type of license plate as a new license plate, the identification unit 226 will identify the bicycle as a specified small moped. Also, if the vehicle type identification unit 222 identifies a two-wheeled vehicle as a kick scooter, and the license plate identification unit 224 identifies the type of license plate as "white + green border," the identification unit 226 will identify the kick scooter as a small two-wheeled vehicle. The identified motorcycle information is transmitted to the entrance reception machine 50.

[0028] Furthermore, the identification device 220 can subdivide two-wheeled vehicles and identify whether they are motorcycles or kick scooters, provided it has at least a vehicle type identification unit 222. In other words, if it is not necessary to identify more subdivided categories as shown in Figure 1, and it is sufficient to identify the type of two-wheeled vehicle based on the shape of the vehicle body viewed from the side, the two-wheeled vehicle identification system 20 does not need to have a rear camera 214, a plate identification unit 224, and an identification unit 226. In this case, the information of the two-wheeled vehicle identified by the vehicle type identification unit 222 is transmitted from the identification device 220 to the entrance reception machine 50.

[0029] Compared to conventional loop coil type vehicle identification devices, this type of motorcycle identification system 20 offers the following advantages, for example: (1) Can identify a kick scooter (2) This reduces false detection of motorcycles with a low amount of metal in the body. (3) This reduces false detection of bicycles with a large amount of metal in the frame (such as electric bicycles and bicycles equipped with child seats). (4) It can identify children's bicycles with a small amount of metal in the frame.

[0030] The admission ticket machine 50 is connected to the identification device 220 and can issue admission tickets. Admission tickets are issued when the ticket issuance button on the admission ticket machine 50 is pressed, and the issued admission ticket has a classification identified by the identification device 220 printed on it.

[0031] The flap-type gate (an example of a gate) 60 is positioned at the entrance to the access route to the bicycle parking space and is configured to allow one motorcycle at a time to enter. The opening and closing of the flap-type gate 60 is controlled by the admission reception machine 50.

[0032] Next, we will explain the operation of the bicycle parking management system 10, following the flow of a user riding a motorcycle using the bicycle parking area. A user on a motorcycle enters the parking area and stops in front of the flap-type gate 60 and in front of the entrance reception machine 50. The stopped motorcycle comes into the field of view of the side camera 212 and the rear camera 214.

[0033] At predetermined timings, the side camera 212 acquires an image of the side of the motorcycle, and the rear camera 214 acquires an image of the license plate. Here, this predetermined timing is, for example, as follows: (1) When the ticket issuing button on the admission reception machine 50 is pressed by the user (2) When a reaction is detected in the loop coil (not shown) embedded in the entrance (3) When the side camera 214 has a motion detection function and an event occurs due to this motion detection function However, images may be acquired continuously by the side camera 212, rather than at predetermined timings.

[0034] The primary vehicle processing unit 222a detects the presence of a motorcycle based on a side view image of the motorcycle using a first machine learning model and identifies the type of motorcycle detected. It also outputs information about the location of region A where the motorcycle is located. The secondary vehicle processing unit 222b identifies and classifies the type of motorcycle using a second machine learning model based on an extracted image that includes region A, which is extracted from the side view image of the motorcycle.

[0035] Here, as mentioned above, the first machine learning model is a machine learning model used for object detection, and therefore tends to have a lower accuracy in identifying the type of motorcycle compared to the second machine learning model, which is specialized in category classification. Therefore, the vehicle type identification unit 222 identifies the result as the final vehicle type when the result R1, which is the type of motorcycle identified by the primary vehicle type processing unit 222a, and the result R2, which is the type of motorcycle identified by the secondary vehicle type processing unit 222b, match.

[0036] However, if the result R1 identified by the primary vehicle processing unit 222a and the result R2 identified by the secondary vehicle processing unit 222b do not match, the vehicle identification unit 222 compares the accuracy of the result R2 identified by the secondary vehicle processing unit 222b with a preset threshold, and if it determines that the accuracy is higher than this threshold, it adopts the result R2 identified by the secondary vehicle processing unit 222b. Furthermore, in the following cases, the vehicle identification unit 222 will determine that no motorcycles exist. (1) If the primary vehicle processing unit 222a fails to detect a motorcycle (2) Regardless of the result R1 identified by the primary vehicle processing unit 222a and the result R2 identified by the secondary vehicle processing unit 222b, if the accuracy of both result R1 and result R2 is lower than a preset threshold,

[0037] Meanwhile, the primary plate processing unit 224a detects the license plate using a third machine learning model based on the license plate image and outputs information about the location of the detected license plate in region B. The secondary plate processing unit 224b identifies and classifies the type of license plate using a fourth machine learning model based on the cropped image obtained by cutting out the license plate image to include region B. The plate identification unit 224 identifies the type of license plate as the final license plate type when the accuracy of the type of license plate classified by the secondary plate processing unit 224a is higher than a preset threshold.

[0038] Subsequently, the identification unit 226 identifies the motorcycle's classification according to the matrix shown in Figure 1, based on the type of motorcycle identified by the vehicle type identification unit 222 and the type of license plate identified by the license plate identification unit 224.

[0039] The information of the category identified by the identification unit 226 is transmitted to the admission reception machine 50. The admission reception machine 50 issues an admission ticket printed with the received category information. Upon receiving their admission ticket, the flap-type gate 60 opens, allowing the user to proceed to the bicycle parking area.

[0040] After finishing their use of the bicycle parking area, users pay the designated parking fee at the payment machine and exit through the gate located at the exit. In a bicycle parking area managed by the bicycle parking management system 10, the prescribed parking fee can be set according to the classification of the two-wheeled vehicle (see Figure 1).

[0041] As explained above, the bicycle parking management system 10 and the motorcycle identification system 20 include an identification device 220 equipped with a primary vehicle type processing unit 222a and a first machine learning model and a second machine learning model with different functions, respectively, so that the type of motorcycle can be identified with a higher degree of accuracy. Furthermore, the bicycle parking management system 10 and the motorcycle identification system 20 identify motorcycles based on a combination of motorcycle type and license plate type, allowing for more detailed identification of motorcycle types.

[0042] Although embodiments of the present invention have been described above, the present invention is not limited to the above-described forms, and any changes to the conditions, etc., that do not depart from the gist of the invention are all within the scope of application of the present invention. [Explanation of Symbols]

[0043] 10. Bicycle Parking Management System 12a Bicycle 12b Class 1 Moped 20 Motorcycle Identification System 50 Admission reception machines 60 Flap-type gate 212 Side camera 214 Rear Camera 220 Identification device 222 Vehicle-Specific Section 222a Primary Vehicle Processing Unit 222b Secondary vehicle processing unit 224 Plate Identification Part 224a Primary plate processing unit 224b Secondary plate processing unit 226 Identification unit

Claims

1. A first camera for acquiring a first image, which is an image of the side of a motorcycle, A second camera for acquiring a second image, which is an image of the license plate of the aforementioned motorcycle, A motorcycle identification system comprising: an identification device that identifies at least the legally defined classification of the motorcycle based on the first image and the second image.

2. The identification device includes a vehicle type identification unit that identifies from the first image whether the two-wheeled vehicle is a bicycle, a motorcycle, or a kick scooter, From the second image, a plate identification unit identifies the type of license plate, A motorcycle identification system according to claim 1, further comprising: an identification unit that identifies the classification based on the type of motorcycle identified by the vehicle type identification unit and the type of license plate identified by the license plate identification unit.

3. The identification device includes a vehicle type identification unit that identifies from the first image whether the two-wheeled vehicle is a bicycle, a motorcycle, or a kick scooter, From the second image, a plate identification unit identifies the type of license plate, A motorcycle identification system according to claim 1, comprising: an identification unit that identifies which of the following categories the classification is: 1) bicycle, 2) moped (50cc class), 3) moped (50cc class), 4) small motorcycle, 5) specific small moped, 6) kick scooter, and 7) light motorcycle, based on the type of motorcycle identified by the vehicle type identification unit and the type of license plate identified by the license plate identification unit.

4. The vehicle identification unit detects the motorcycle using a first machine learning model that has been trained to detect the motorcycle based on the first image, and outputs information about the region A where the detected motorcycle is located. A motorcycle identification system according to claim 2 or 3, comprising: a secondary vehicle type processing unit that identifies the type of motorcycle based on a cropped image obtained by cropping out from the first image to include the region A, using a second machine learning model trained to classify the motorcycle; and a secondary vehicle type processing unit that identifies the type of motorcycle based on a cropped image obtained by cropping out from the first image to include the region A.

5. The plate identification unit detects the license plate using a third machine learning model that has been trained to detect the license plate based on the second image, and outputs information about the region B where the detected license plate is located. A motorcycle identification system according to claim 4, comprising: a secondary plate processing unit that identifies the type of license plate based on a cropped image obtained by cropping out from the second image to include the region B, using a fourth machine learning model trained to classify the license plate; and a secondary plate processing unit that identifies the type of license plate.

6. The motorcycle identification system according to claim 5, wherein the primary vehicle processing unit identifies the type of motorcycle detected.

7. The motorcycle identification system according to claim 6, wherein the vehicle type identification unit identifies the result as the type of motorcycle when the result identified by the primary vehicle type processing unit matches the result identified by the secondary vehicle type processing unit.

8. The motorcycle identification system according to claim 7, wherein if the primary vehicle processing unit fails to detect the motorcycle, it is determined that the motorcycle does not exist.

9. The motorcycle identification system according to claim 8, wherein the first camera is positioned out of reach of children and in a position that can acquire an image capturing the characteristics of the motorcycle.

10. A camera for acquiring images of the side of a motorcycle, The vehicle comprises an identification device that identifies the type of motorcycle based on the aforementioned image, The identification device includes a primary vehicle processing unit that detects the motorcycle using a first machine learning model trained to detect the motorcycle based on the image, and outputs information about the region A where the detected motorcycle is located. A motorcycle identification system comprising: a secondary vehicle type processing unit that classifies the type of motorcycle based on a cropped image obtained by cropping the aforementioned image to include the region A, using a second machine learning model trained to classify the motorcycle.

11. A first camera for acquiring a first image, which is an image of the side of a motorcycle, A second camera for acquiring a second image, which is an image of the license plate of the aforementioned motorcycle, An identification device that identifies at least the legally defined classification of the motorcycle based on the first image and the second image, A bicycle parking management system comprising: an admission reception machine that issues admission tickets printed with the classification identified by the aforementioned identification device.

12. A camera for acquiring images of the side of a motorcycle, An identification device for identifying the type of motorcycle based on the aforementioned image, The system includes an admission reception machine that issues admission tickets on which the type of motorcycle identified by the identification device is printed, The identification device includes a primary vehicle processing unit that detects the motorcycle using a first machine learning model trained to detect the motorcycle based on the image, and outputs information about the region A where the detected motorcycle is located. A parking management system comprising: a secondary vehicle type processing unit that classifies the type of motorcycle based on a cropped image obtained from the aforementioned image to include the region A, using a second machine learning model trained to classify the motorcycle.

Images