Parking lot vehicle entry / exit management program and vehicle entry / exit management device

Abstract

To provide a vehicle entry / exit management program and a vehicle entry / exit management device for a parking lot, with an installation cost reduced.SOLUTION: In step 701, vehicle front side image data is acquired. In step 702, the vehicle front side image data is input to determine whether entry side vehicle front side image data has been extracted using a trained vehicle front side image training control model that extracts a feature quantity using training vehicle front side image data as input data. In step 703, a vehicle number is recognized from the extracted entry side vehicle front side image data. In step 704, a bar of an entry unit is raised. In step 705, vehicle rear side image data is acquired. In step 706, the vehicle rear side image data is input to determine whether entry side vehicle rear side image data has been extracted using a trained vehicle rear side image training control model that extracts a feature quantity using training vehicle rear side image data as input data. In step 707, the bar of the entry unit is lowered.SELECTED DRAWING: Figure 7

Description

Technical Field

[0001] The present invention relates to a vehicle entry / exit management program and a vehicle entry / exit management device for a parking lot.

Background Art

[0002] In a conventional vehicle entry / exit management device for a parking lot, gate machines for raising / lowering a bar for stopping a vehicle from passing are provided at the entrance and exit of the parking lot.

[0003] In the above-described conventional vehicle entry / exit management device for a parking lot, a ticket dispenser is provided in the entrance-side gate machine, and an entrance-side loop coil is embedded near the entrance-side gate machine to detect a vehicle. As a result, after a vehicle is detected by the entrance-side loop coil and an operator operates the ticket dispenser, the bar of the entrance-side gate machine rises. After the vehicle passes through the entrance-side gate machine, the bar of the entrance-side gate machine descends. On the other hand, a payment machine is provided in the exit-side gate machine, and an exit-side loop coil is embedded near the exit-side gate machine to detect a vehicle. As a result, after a vehicle is detected by the exit-side loop coil and an operator operates the payment machine, the bar of the exit-side gate machine rises. After the vehicle passes through the exit-side gate machine, the bar of the exit-side gate machine descends.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, in the above-described conventional vehicle entry / exit management device for a parking lot, since a loop coil is embedded near the gate machine, there is a problem that the equipment cost is high.

Means for Solving the Problems

[0006] In order to solve the above problems, a vehicle entry / exit management program for a parking lot according to the present invention is for a parking lot including a gate machine having a bar for entry or exit, a vehicle front camera provided near the gate machine for acquiring a front image of a vehicle heading towards the bar, and a vehicle rear camera provided near the gate machine for acquiring a rear image of a vehicle moving away from the bar, the program including a vehicle front image extraction procedure for extracting vehicle front image data of a vehicle from an image of the vehicle front camera, a vehicle number acquisition procedure for acquiring the vehicle number of the vehicle after extracting the vehicle front image data, a bar raising procedure for raising the bar after acquiring the vehicle number, a vehicle rear image extraction procedure for extracting vehicle rear image data of the vehicle from an image of the vehicle rear camera after raising the bar, and a bar lowering procedure for lowering the bar after extracting the vehicle rear image data After extracting the rear vehicle image data when the vehicle is stored, a management order creation start procedure for starting the creation of a management order for the vehicle, and and is for causing a computer to execute the same.

[0007] After extracting the rear vehicle image data when the vehicle is stored, a management order creation start means for starting the creation of a management order for the vehicle, and A vehicle entry / exit management device for a parking lot according to the present invention includes a gate machine having a bar for entry or exit, a vehicle front camera provided near the gate machine for acquiring a front image of a vehicle heading towards the bar, and a vehicle rear camera provided near the gate machine for acquiring a rear image of a vehicle moving away from the bar, and includes vehicle front image extraction means for extracting vehicle front image data of a vehicle from an image of the vehicle front camera, vehicle number acquisition means for acquiring the vehicle number of the vehicle after extracting the vehicle front image data, bar raising means for raising the bar after acquiring the vehicle number, vehicle rear image extraction means for extracting vehicle rear image data of the vehicle from an image of the vehicle rear camera after raising the bar, and bar lowering means for lowering the bar after extracting the vehicle rear image data

Advantages of the Invention

[0008] According to the present invention, since a loop coil is not required, equipment costs can be reduced.

Brief Description of the Drawings

[0009]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Figure 16

Embodiments for Carrying Out the Invention

[0010] FIG. 1 is a diagram showing a parking lot including a first embodiment of a vehicle entry / exit management device according to the present invention. In FIG. 1, a vehicle entrance IN is dedicated to vehicle entrance, and a vehicle exit OUT is dedicated to vehicle exit.

[0011] In FIG. 1, for example, four vehicle compartments 10-1, 10-2, 10-3, and 10-4 are provided in the parking lot 10. An entrance unit 20 is provided at the vehicle entrance IN, and an exit unit 30 is provided at the vehicle exit OUT. The entrance unit 20 and the exit unit 30 are connected to a vehicle entry / exit management device 40. An accounting machine 40a is connected to the vehicle entry / exit management device 40 within or in the vicinity of the parking lot 10 at a distance. Further, the vehicle entry / exit management device 40 is connected to an information terminal 60 or the like via the Internet 50 as necessary. An operator can operate the vehicle entry / exit management device 40 via the information terminal 60 or directly.

[0012] FIG. 2 is a diagram showing the entrance unit 20 of FIG. 1.

[0013] As shown in FIG. 2, the entrance unit 20 includes a bar 21, a gate machine 22 for raising and lowering the bar 21, a vehicle front camera (for example, a monocular camera) 24 for acquiring a front image of the vehicle W fixed below the pole 23, and a vehicle rear camera (for example, a monocular camera) 25 for acquiring a rear image of the vehicle W fixed above the pole 23.

[0014] FIG. 3 is a diagram showing the exit unit 30 of FIG. 1.

[0015] As shown in FIG. 3, the exit unit 30 includes a bar 31, a gate machine 32 for raising and lowering the bar 31, a vehicle front camera (for example, a monocular camera) 34 for acquiring a front image of the vehicle W fixed below the pole 33, and a vehicle rear camera (for example, a monocular camera) 35 for acquiring a rear image of the vehicle W fixed above the pole 33.

[0016] FIG. 4 is a detailed block circuit diagram of the vehicle entry / exit management device 40 of FIG. 1.

[0017] In FIG. 4, the vehicle entry / exit management device 40 is configured by a computer, and specifically includes a central processing unit (CPU) 41, a read-only memory (ROM) 42 for storing programs and the like, a flash memory 43, a random access memory (RAM) 44 for storing temporary data and the like, an input / output (I / O) interface 45 having USB (registered trademark) terminals, interrupt terminals INT1, INT2, etc., an image interface 46 connected to cameras 24, 25, 34, 35, a communication interface 47 connected to the Internet 3, a vehicle front image learning control model 48, a vehicle rear image learning control model 49, etc. Each of the learning control models 48, 49 is a neural network based on deep learning composed of an input layer, a plurality of intermediate layers, and an output layer. In the neural network, the weights and biases of the multi-layer perceptron are adjusted by the error backpropagation method for learning.

[0018] FIG. 5 is a vehicle front image learning operation routine executed by the CPU 41 by an interrupt from an operator to the terminal INT1. This learning operation routine is stored in the ROM 42 or the flash memory 43.

[0019] First, in step 501, a plurality of vehicle front image data for learning recognized by the operator are acquired from the vehicle front cameras 24, 34 or a USB memory or the like acquired in advance. The larger the number of recognized vehicle front image data for learning, the greater the learning effect in step 502.

[0020] In step 502, vehicle front image learning processing is performed. That is, the vehicle front image learning control model 48 that extracts feature amounts using the recognized large number of vehicle front image data for learning as input data is learned by deep learning.

[0021] Then, the routine of FIG. 5 ends in step 503.

[0022] FIG. 6 is a vehicle rear image learning operation routine executed by the CPU 41 due to an interrupt by an operator for the terminal INT2. This learning operation routine is stored in the ROM 42 or the flash memory 43.

[0023] First, in step 601, a plurality of learning vehicle rear image data recognized by the operator is acquired from the vehicle rear cameras 25 and 35 or a USB memory or the like acquired in advance. The larger the number of recognized learning vehicle rear image data, the greater the learning effect in step 602.

[0024] In step 602, vehicle rear image learning processing is performed. That is, a vehicle rear image learning control model 49 that extracts feature amounts using the recognized large number of learning vehicle rear image data as input data is learned by deep learning.

[0025] Then, the routine in FIG. 6 ends in step 603.

[0026] Note that the learning operations in FIGS. 5 and 6 can be executed by the operator at any time thereafter, and the learning values are updated. Further, it may be executed on the cloud side connected to the Internet 50, and the learning result may be introduced into the learning control model 48 via the Internet 50.

[0027] FIG. 7 is a flowchart showing details of a warehousing routine (main routine 1) executed by the CPU 41. In this case, in FIG. 2, it is assumed that the vehicle W is traveling from outside the parking lot 10 toward the warehousing unit 20.

[0028] First, in step 701, image data of the vehicle front camera 24 is acquired.

[0029] Next, in step 702, using the learned vehicle front image learning control model 48 that extracts feature amounts with the recognized vehicle front image data for learning as input data, the image data of the vehicle front camera 24 is input to determine whether the in-warehouse side vehicle front image data has been extracted. When the in-warehouse side vehicle front image data has been extracted, the process proceeds to step 703. If the in-warehouse side vehicle front image data has not been extracted, the process returns to step 701 and the above-described processing is repeated.

[0030] Next, in step 703, the vehicle number is recognized from the vehicle front image data extracted in step 702. That is, the vehicle number recognition process includes a binary data conversion procedure for converting the vehicle front image data extracted in step 702 into binary data, a rectangular contour region extraction procedure for extracting the connected black data or the connected contour of white data of the binary data as a plurality of rectangular contour regions, a number and dot region discrimination and extraction procedure for discriminating and extracting a plurality of number regions and dot regions from the plurality of rectangular contour regions, and a vehicle number extraction procedure for extracting the vehicle number of the vehicle from the number regions and dot regions. The number and dot region discrimination and extraction procedure includes a Boolean image conversion procedure for converting the image within each rectangular contour region into a Boolean image, and a number and dot discrimination and extraction procedure for comparing the Boolean image with a Boolean number template by a pixel-by-pixel Boolean operation and discriminating and extracting each rectangular contour region as a number and dot region when the similarity between the Boolean image and the Boolean number template is greater than or equal to a first threshold or less than or equal to a second threshold smaller than the first threshold. The vehicle number extraction processing procedure includes an average value calculation procedure for calculating the average height of all of the number and dot regions, a first selection procedure for selecting one of the number and dot regions as a first region, a second selection procedure for selecting a number and dot region within a range of a predetermined multiple of the average height on the right side of the first region as a second region, a third selection procedure for selecting a number and dot region between the first and second regions as a third region, a vehicle number candidate selection procedure for setting the first, second, and third regions as vehicle number candidates when the third region is a predetermined number, and a vehicle number selection procedure for selecting the vehicle number candidate as the vehicle number of the vehicle if there is one vehicle number candidate, or selecting the vehicle number candidate that is most likely to satisfy a predetermined condition as the vehicle number of the vehicle if there are multiple vehicle number candidates (see Patent Document 1).

[0031] Next, in step 704, the gate machine 22 of the warehousing unit 20 raises the bar 21. As a result, the vehicle W can pass under the bar 21.

[0032] When the vehicle W passes under the bar 21, in step 705, the image data of the rear vehicle camera 25 is acquired.

[0033] Next, in step 706, using the learned vehicle rear image learning control model 49 that extracts feature amounts with the recognized learning vehicle rear image data as input data, the image data of the vehicle rear camera 25 is input to determine whether the in-warehouse side vehicle rear image data has been extracted. When the in-warehouse side vehicle rear image data has been extracted, the process proceeds to step 707, and if the in-warehouse side vehicle rear image data has not been extracted, the process returns to step 705.

[0034] Next, in step 707, the gate machine 22 of the warehousing unit 20 lowers the bar 21.

[0035] Finally, in step 708, creating the management order is started on the flash memory 43 or the RAM 44. Note that, for example, the management order is composed of the warehousing time, the vehicle number, the vehicle front image data at the time of warehousing, and the vehicle rear image data at the time of warehousing for each management order number.

[0036] FIG. 8 is a flowchart showing details of the outbound routine (main routine 2) executed by the CPU 41. In this case, in FIG. 3, it is assumed that the vehicle W is traveling from within the parking lot 10 toward the outbound unit 30.

[0037] First, in step 801, the image data of the vehicle front camera 34 is acquired.

[0038] Next, in step 802, using the learned vehicle front image learning control model 48 that extracts feature amounts with the recognized learning vehicle front image data by the operator as input data, the image data of the vehicle front camera 34 is input to determine whether the outbound side vehicle front image data has been extracted. When the outbound side vehicle front image data has been extracted, the process proceeds to step 803, and if the outbound side vehicle front image data has not been extracted, the process returns to step 801 and the above-described processing is repeated.

[0039] Next, in step 803, a vehicle number is recognized from the vehicle front image data extracted in step 802. That is, the vehicle number recognition process includes a binary data conversion procedure for converting the vehicle front image data extracted in step 802 into binary data, a rectangular contour area extraction procedure for extracting the connected black data or the connected contour of white data of the binary data as a plurality of rectangular contour areas, a number / dot area discrimination and extraction procedure for discriminating and extracting a plurality of number areas and dot areas from the plurality of rectangular contour areas, and a vehicle number extraction procedure for extracting the vehicle number of the vehicle from the number areas and dot areas. The number / dot area discrimination and extraction procedure includes a Boolean type image conversion procedure for converting the image within each rectangular contour area into a Boolean type image, and a number / dot discrimination and extraction procedure for comparing the Boolean type image with a Boolean type number template by a pixel-by-pixel Boolean operation and discriminating and extracting each rectangular contour area as a number / dot area when the similarity between the Boolean type image and the Boolean type number template is equal to or greater than a first threshold value or equal to or less than a second threshold value smaller than the first threshold value. The vehicle number extraction processing procedure includes an average value calculation procedure for calculating the average height of all of the number / dot areas, a first selection procedure for selecting one of the number / dot areas as a first area, a second selection procedure for selecting a number / dot area within a range of a predetermined multiple of the average height on the right side of the first area as a second area, a third selection procedure for selecting a number / dot area between the first and second areas as a third area, a vehicle number candidate selection procedure for setting the first, second, and third areas as vehicle number candidates when the third area is a predetermined number, and a vehicle number selection procedure for selecting the vehicle number candidate as the vehicle number of the vehicle if there is one vehicle number candidate, or selecting the vehicle number candidate that is most likely to satisfy a predetermined condition as the vehicle number of the vehicle if there are a plurality of vehicle number candidates (see Patent Document 1).

[0040] Next, in step 804, it is determined whether or not settlement has been performed by the calculator 40a. Usually, settlement is performed by the calculator 40a in advance. If settlement has not been performed, wait for settlement and proceed to the next step 805. Alternatively, even if settlement has not been performed, it is also possible to proceed to the next step 805 and record "unsettled" at the end of the creation of the management order in step 809 described later.

[0041] Next, in step 805, the gate machine 32 of the shipping unit 30 raises the bar 31. As a result, the vehicle W can pass under the bar 31.

[0042] When the vehicle W passes under the bar 31, in step 806, the image data of the rear vehicle camera 35 is acquired.

[0043] Next, in step 807, using the learned rear vehicle image learning control model 49 that extracts feature amounts with the recognized learned rear vehicle image data as input data, the image data of the rear vehicle camera 35 is input to determine whether the shipping-side rear vehicle image data has been extracted. When the shipping-side rear vehicle image data has been extracted, the process proceeds to step 808, and if the shipping-side rear vehicle image data has not been extracted, the process returns to step 806.

[0044] Next, in step 808, the gate machine 32 of the shipping unit 30 lowers the bar 31.

[0045] Finally, in step 809, the creation of the management order is started on the flash memory 43 or the RAM 44. Note that, for example, the management order is composed of the arrival time, vehicle number, front vehicle image data at the time of arrival, rear vehicle image data at the time of arrival, departure time, front vehicle image data at the time of departure, and rear vehicle image data at the time of departure for each management order number.

[0046] Note that the arrival routine (main routine 1) in FIG. 7 and the arrival routine (main routine 2) in FIG. 8 are both main routines, and thus are executed in parallel by a multi-process.

[0047] The vehicle in-out management device in FIG. 4 can also be configured with the hardware shown in FIG. 9.

[0048] In FIG. 9, in a parking lot comprising a gate machine 22(32) having a bar 21(31) for vehicle entry or exit, a front vehicle camera 24(34) provided near the gate machine 22(32) for acquiring a front image of the vehicle W facing the bar 21(31), and a rear vehicle camera 25(35) provided near the gate machine 22(32) for acquiring a rear image of the vehicle W leaving the bar 21(31), the vehicle entry / exit management device includes a front vehicle image extraction means 901 for extracting front vehicle image data of the vehicle W from the image of the front vehicle camera 24(34), a vehicle number acquisition means 902 for acquiring the vehicle number of the vehicle W after extracting the front vehicle image data, a bar raising means 903 for raising the bar 21(31) after acquiring the vehicle number, a rear vehicle image extraction means 904 for extracting rear vehicle image data of the vehicle W from the image of the rear vehicle camera 25(35) after the bar 21(31) is raised, and a bar lowering means 905 for lowering the bar 21(31) after extracting the rear vehicle image data.

[0049] FIG. 10 is a diagram showing a parking lot including a second embodiment of the vehicle entry / exit management device according to the present invention. In FIG. 10, the vehicle entry / exit G is both a vehicle entrance and a vehicle exit.

[0050] In FIG. 10, an entry / exit unit 20' is provided at the vehicle entry / exit G, and the entry / exit unit 20' is connected to the vehicle entry / exit management device 40'.

[0051] FIG. 11 is a diagram showing the entry / exit unit 20' of FIG. 10.

[0052] As shown in FIG. 11, the warehousing and outbound unit 20’ is composed of a bar 21’, a gate machine 22’ for raising and lowering the bar 21’, an outward camera (for example, a monocular camera) 24’ for acquiring a front image or a rear image of the vehicle W fixed below the pole 23’, and an inward camera (for example, a monocular camera) 25’ for acquiring a rear image or a front image of the vehicle W fixed above the pole 23’. That is, the outward camera 24’ faces the outside of the parking lot 10. Therefore, when the vehicle W enters the warehouse, a front image of the vehicle W is acquired. On the other hand, when the vehicle W exits the warehouse, a rear image of the vehicle W is acquired. Also, the inward camera 25’ faces the inside of the parking lot 10. Therefore, when the vehicle W enters the warehouse, a rear image of the vehicle W is acquired. On the other hand, when the vehicle W exits the warehouse, a front image of the vehicle W is acquired.

[0053] FIG. 12 is a detailed block circuit diagram of the vehicle warehousing and outbound management device 40’ in FIG. 10.

[0054] In FIG. 12, the outward camera 24’ and the inward camera 25’ are connected to the image interface 46 of the vehicle warehousing and outbound management device 40’.

[0055] FIG. 13 is a flowchart showing the main routine executed by the CPU 41 in FIG. 12.

[0056] The routine of FIG. 13 is substantially executed when the vehicle W approaches the loading / unloading unit 20'. That is, at the time of loading, the vehicle is detected by the outward-facing camera 24' and its image is acquired. On the other hand, at the time of unloading, the vehicle is detected by the inward-facing camera 25' and its image is acquired. Therefore, in step 1301, it is determined whether there is an image of the vehicle in the outward-facing camera 24', that is, whether the vehicle is at the time of loading. On the other hand, in step 1302, it is determined whether there is an image of the vehicle in the inward-facing camera 25', that is, whether the vehicle is at the time of unloading. Note that in steps 1301 and 1302, it is not necessary to determine whether the vehicle is in front or behind. As a result, when it is determined that the vehicle is at the time of loading, the process proceeds to step 1303 to perform the loading process. On the other hand, when it is determined that the vehicle is at the time of unloading, the process proceeds to step 1304 to perform the unloading process. When the vehicle does not exist, the process returns to step 1301.

[0057] FIG. 14 is a flowchart showing details of the loading process step 1303 of FIG. 13.

[0058] In step 1401, the image data of the outward-facing camera 24' is acquired.

[0059] Next, in step 1402, using the learned vehicle front image learning control model 48 that extracts feature amounts with the recognized learned vehicle front image data as input data, the image data of the outward-facing camera 24' is input to determine whether vehicle front image data has been extracted. When the vehicle front image data has been extracted, the process proceeds to step 1403. If the vehicle front image data has not been extracted, the process returns to step 1401 and the above-described process is repeated.

[0060] Next, in step 1403, a vehicle number is recognized from the vehicle front image data extracted in step 1402. That is, the vehicle number recognition process includes a black-and-white binary data conversion procedure for converting the vehicle front image data extracted in step 1402 into black-and-white binary data, a rectangular contour area extraction procedure for extracting the connected black data or the connected contour of white data of the black-and-white binary data as a plurality of rectangular contour areas, a number and dot area discrimination and extraction procedure for discriminating and extracting a plurality of number areas and dot areas from the plurality of rectangular contour areas, and a vehicle number extraction procedure for extracting the vehicle number of the vehicle from the number areas and dot areas. The number and dot area discrimination and extraction procedure includes a Boolean image conversion procedure for converting the image within each rectangular contour area into a Boolean image, and a number and dot discrimination and extraction procedure for comparing the Boolean image with a Boolean number template by a pixel-by-pixel Boolean operation and discriminating and extracting each rectangular contour area as a number and dot area when the similarity between the Boolean image and the Boolean number template is greater than or equal to a first threshold value or less than or equal to a second threshold value smaller than the first threshold value. The vehicle number extraction processing procedure includes an average value calculation procedure for calculating the average height of all of the number and dot areas, a first selection procedure for selecting one of the number and dot areas as a first area, a second selection procedure for selecting a number and dot area within a range of a predetermined multiple of the average height on the right side of the first area as a second area, a third selection procedure for selecting a number and dot area between the first and second areas as a third area, a vehicle number candidate selection procedure for setting the first, second, and third areas as vehicle number candidates when the third area is a predetermined number, and a vehicle number selection procedure for selecting the vehicle number candidate as the vehicle number of the vehicle if there is one vehicle number candidate, or selecting the vehicle number candidate that is most likely to satisfy a predetermined condition as the vehicle number of the vehicle if there are a plurality of vehicle number candidates (see Patent Document 1).

[0061] Next, in step 1404, the bar 21' is raised by the gate machine 22' of the warehousing and outbound unit 20'. As a result, the vehicle W can pass under the bar 21'.

[0062] When the vehicle W passes under the bar 21', in step 1405, the image data of the inward camera 25' is acquired.

[0063] Next, in step 1406, using the learned vehicle rear image learning control model 49 that extracts feature amounts with the recognized learning vehicle rear image data as input data, the image data of the inward camera 25' is input to determine whether vehicle rear image data has been extracted. When the vehicle rear image data has been extracted, the process proceeds to step 1407; if the vehicle rear image data has not been extracted, the process returns to step 1405.

[0064] Next, in step 1407, the bar 21' is lowered by the gate machine 22' of the warehousing and shipping unit 20'.

[0065] Finally, in step 1408, the creation of the management order is started on the flash memory 43 or the RAM 44. Note that, for example, the management order is composed of the warehousing time, vehicle number, vehicle front image data at the time of warehousing, and vehicle rear image data at the time of warehousing for each management order number.

[0066] FIG. 15 is a flowchart showing the details of the shipping process step 1304 in FIG. 13.

[0067] In step 1501, the image data of the inward camera 25' is acquired.

[0068] Next, in step 1502, using the learned vehicle front image learning control model 48 that extracts feature amounts with the recognized learning vehicle front image data by the operator as input data, the image data of the inward camera 25' is input to determine whether vehicle front image data has been extracted. When the vehicle front image data has been extracted, the process proceeds to step 1503; if the vehicle front image data has not been extracted, the process returns to step 1501 and the above-described processing is repeated.

[0069] Next, in step 1503, a vehicle number is recognized from the vehicle front image data extracted in step 1502. That is, the vehicle number recognition process includes a binary data conversion procedure for converting the vehicle front image data extracted in step 1502 into binary data, a rectangular contour region extraction procedure for extracting the connected black data or the connected contour of white data of the binary data as a plurality of rectangular contour regions, a number / dot region extraction procedure for discriminating and extracting a plurality of number regions and dot regions from the plurality of rectangular contour regions, and a vehicle number extraction procedure for extracting the vehicle number of the vehicle from the number regions and dot regions. The number / dot region extraction procedure includes a Boolean-type image conversion procedure for converting the image within each rectangular contour region into a Boolean-type image, and a number / dot discrimination extraction procedure for comparing the Boolean-type image with a Boolean-type number template by a pixel-by-pixel Boolean operation and discriminating and extracting each rectangular contour region as a number / dot region when the similarity between the Boolean-type image and the Boolean-type number template is equal to or greater than a first threshold value or less than a second threshold value smaller than the first threshold value. The vehicle number extraction processing procedure includes an average value calculation procedure for calculating the average height of all of the number / dot regions, a first selection procedure for selecting one of the number / dot regions as a first region, a second selection procedure for selecting a number / dot region within a range of a predetermined multiple of the average height on the right side of the first region as a second region, a third selection procedure for selecting a number / dot region between the first and second regions as a third region, a vehicle number candidate selection procedure for setting the first, second, and third regions as vehicle number candidates when the third region is a predetermined number, and a vehicle number selection procedure for selecting the vehicle number candidate as the vehicle number of the vehicle if there is one vehicle number candidate, or selecting the vehicle number candidate that is most likely to satisfy a predetermined condition as the vehicle number of the vehicle if there are a plurality of vehicle number candidates (see Patent Document 1).

[0070] Next, in step 1504, it is determined whether or not settlement has been performed by the settlement machine 40a. Usually, settlement is performed by the settlement machine 40a in advance. If settlement has not been performed, wait for settlement and proceed to the next step 1505. Alternatively, even if settlement has not been performed, it is also possible to proceed to the next step 1505 and record "unsettled" at the end of the creation of the management order in step 1509 described later.

[0071] Next, in step 1505, the bar 21' is raised by the gate machine 22' of the warehousing and shipping unit 20'. As a result, the vehicle W can pass under the bar 21'.

[0072] When the vehicle W passes under the bar 21', in step 1506, the image data of the outward camera 24' is acquired.

[0073] Next, in step 1507, using the learned vehicle rear image learning control model 49 that extracts feature amounts with the recognized learned vehicle rear image data as input data, the image data of the outward camera 24' is input to determine whether vehicle rear image data has been extracted. When the vehicle rear image data has been extracted, the process proceeds to step 1508, and if the vehicle rear image data has not been extracted, the process returns to step 1506.

[0074] Next, in step 1508, the bar 21' is lowered by the gate machine 22' of the warehousing and shipping unit 20'.

[0075] Finally, in step 1509, the creation of the management order is started on the flash memory 43 or the RAM 44. Note that, for example, the management order is composed of the warehousing time, vehicle number, vehicle front image data at the time of warehousing, vehicle rear image data at the time of warehousing, shipping time, vehicle front image data at the time of shipping, and vehicle rear image data at the time of shipping for each management order number.

[0076] The vehicle warehousing and shipping management device in FIG. 12 can also be configured with the hardware shown in FIG. 16.

[0077] In FIG. 16, there is a parking lot having a gate machine 22' with a bar 21' for entry and exit, an outward-facing camera 24' provided near the gate machine 22', and an inward-facing camera 25' provided near the gate machine 22'. The vehicle entry / exit management device, when the first vehicle W1 enters the warehouse, includes a first vehicle front image extraction means 1601-1 for extracting first vehicle front image data of the first vehicle W1 from the image of the outward-facing camera, a first vehicle license plate acquisition means 1602-1 for acquiring the first vehicle license plate number of the first vehicle W1 after extracting the first vehicle front image data, a first bar lifting means 1603-1 for raising the bar 21' after acquiring the first vehicle license plate number, a first vehicle rear image extraction means 1604-1 for extracting first vehicle rear image data of the first vehicle W1 from the image of the inward-facing camera 25' after the bar 21' is raised by the first bar lifting means, and a first bar lowering means 1605-1 for lowering the bar 21' after acquiring the first rear image data. When the second vehicle exits the warehouse, it includes a second vehicle front image extraction means 1602-1 for extracting second vehicle front image data of the second vehicle from the image of the inward-facing camera 25', a second vehicle license plate acquisition means 1602-2 for acquiring the second vehicle license plate number of the second vehicle after extracting the second vehicle front image data, a second bar lifting means 1603-2 for raising the bar 21' after acquiring the second vehicle license plate number, a second vehicle rear image extraction means 1604-2 for extracting second vehicle rear image data of the second vehicle from the image of the outward-facing camera 24' after the bar 21' is raised by the second bar lifting means 1603-2, and a second bar lowering means 1605-2 for lowering the bar 21' after acquiring the second rear image data.

[0078] Note that the present invention can be applied to any modification within the obvious scope of the above-described embodiments.

Industrial Applicability

[0079] The vehicle entry / exit management program and device for a parking lot according to the present invention can be used in a parking lot charging system or the like.

Explanation of Reference Numerals

[0080] 10: Parking lot 10-1, 10-2, 10-3, 10-4: Passenger Compartment 20: Inbound Unit 21: Bar 22: Gate Machine 23: Pole 24: Front Vehicle Camera 25: Rear Vehicle Camera 30: Outbound Unit 31: Bar 32: Gate Machine 33: Pole 34: Front Vehicle Camera 35: Rear Vehicle Camera 20’: In / Outbound Unit 21’: Bar 22’: Gate Machine 23’: Pole 24’: External Camera 25’: Internal Camera 40’, 40: Vehicle In / Outbound Management Device 40a: Cash Register 41: CPU 42: ROM 43: Flash Memory 44: RAM 45: I / O Interface 46: Image Interface 47: Communication Interface 48: Front Vehicle Image Learning Control Model 49: Rear Vehicle Image Learning Control Model 50: Internet 60: Information Terminal IN: Vehicle Entrance OUT: Vehicle Exit G: Vehicle In / Out

Claims

1. A gate machine having a bar for entry or exit, A front vehicle camera provided near the gate machine for acquiring a front image of a vehicle facing the bar, A rear vehicle camera provided near the gate machine for acquiring a rear image of the vehicle leaving the bar A parking lot comprising: A front vehicle image extraction procedure for extracting front vehicle image data of the vehicle from the image of the front vehicle camera, After extracting the front vehicle image data, a vehicle number acquisition procedure for acquiring the vehicle number of the vehicle, After acquiring the vehicle number, a bar raising procedure for raising the bar, After the bar is raised, a rear vehicle image extraction procedure for extracting rear vehicle image data of the vehicle from the image of the rear vehicle camera, After extracting the rear vehicle image data, a bar lowering procedure for lowering the bar, After extracting the rear vehicle image data at the time of entry of the vehicle, a management order creation start procedure for starting creation of a management order for the vehicle A vehicle entry / exit management program for a parking lot to be executed by a computer.

2. A gate machine having a bar for entry and exit, An outward camera provided near the gate machine for acquiring a front image of a first vehicle entering the bar and a rear image of a second vehicle leaving the bar, An inward camera provided near the gate machine for acquiring a rear image of the first vehicle leaving the bar and a front image of the second vehicle entering the bar A parking lot comprising: When the first vehicle enters, A first front vehicle image extraction procedure for extracting first front vehicle image data of the first vehicle from the image of the outward camera, After extracting the first vehicle front image data, a first vehicle number acquisition procedure for acquiring the vehicle number of the first vehicle; After acquiring the first vehicle number, a first bar raising procedure for raising the bar; After the bar is raised by the first bar raising procedure, a first vehicle rear image extraction procedure for extracting first vehicle rear image data of the first vehicle from the image of the inward-facing camera; After extracting the first vehicle rear image data, a first bar lowering procedure for lowering the bar; After extracting the first vehicle rear image data at the time of storage of the first vehicle, a management order creation start procedure for starting the creation of a management order for the first vehicle; to be executed by a computer, At the time of shipment of the second vehicle, A second vehicle front image extraction procedure for extracting second vehicle front image data of the second vehicle from the image of the inward-facing camera; After extracting the second vehicle front image data, a second vehicle number acquisition procedure for acquiring the second vehicle number of the second vehicle; After acquiring the second vehicle number, a second bar raising procedure for raising the bar; After the bar is raised by the second bar raising procedure, a second vehicle rear image extraction procedure for extracting second vehicle rear image data of the second vehicle from the image of the outward-facing camera; After acquiring the second vehicle rear image data, a second bar lowering procedure for lowering the bar; A vehicle in-out management program for a parking lot to be executed by a computer.

3. The vehicle front image extraction procedure is A vehicle in-out management program for a parking lot to be executed by a computer according to claim 1, comprising a vehicle front image estimation and extraction procedure for estimating and extracting the vehicle front image data by using a learned vehicle front learning control model with the learning vehicle front image data as input data and the image of the vehicle front camera as input data.

4. The first vehicle front image extraction procedure or the second vehicle front image extraction procedure is A vehicle entry / exit management program for a parking lot to be executed by a computer according to claim 2, comprising a vehicle front image estimation and extraction procedure for estimating and extracting the first vehicle front image data or the second vehicle front image data using a learned vehicle front learning control model with the learning vehicle front image data as input data and using the image of the outward camera or the inward camera as input data.

5. The vehicle rear image extraction procedure is A vehicle entry / exit management program for a parking lot to be executed by a computer according to claim 1, comprising a vehicle rear image estimation and extraction procedure for estimating and extracting the vehicle rear image data using a learned vehicle rear learning control model with the learning vehicle rear image data as input data and using the image of the vehicle rear camera as input data.

6. The first vehicle rear image extraction procedure or the second vehicle rear image extraction procedure is A vehicle entry / exit management program for a parking lot to be executed by a computer according to claim 2, comprising a vehicle rear image estimation and extraction procedure for estimating and extracting the first vehicle rear image data or the second vehicle rear image data using a learned vehicle rear learning control model with the learning vehicle rear image data as input data and using the image of the inward camera or the outward camera as input data.

7. Further, a vehicle entry / exit management program for a parking lot according to claim 1, for causing a computer to execute a management order creation end procedure for ending the creation of the management order of the vehicle after the extraction of the vehicle rear image data at the time of the vehicle's exit.

8. Further, a vehicle entry / exit management program for a parking lot according to claim 2, for causing a computer to execute a management order creation end procedure for ending the creation of the management order of the second vehicle after the extraction of the second vehicle rear image data at the time of the second vehicle's exit.

9. A gate machine having a bar for entry or exit, A vehicle front camera provided near the gate machine for acquiring a front image of a vehicle heading towards the bar, A vehicle rear camera provided near the gate machine for acquiring a rear image of the vehicle moving away from the bar A parking lot comprising: Vehicle front image extraction means for extracting vehicle front image data of the vehicle from the image of the vehicle front camera, Vehicle number acquisition means for acquiring the vehicle number of the vehicle after extracting the vehicle front image data, Bar raising means for raising the bar after acquiring the vehicle number, Vehicle rear image extraction means for extracting vehicle rear image data of the vehicle from the image of the vehicle rear camera after the bar is raised, Bar lowering means for lowering the bar of the gate machine after acquiring the vehicle rear image data, Management order creation start means for starting creation of a management order for the vehicle after extracting the vehicle rear image data at the time of entry of the vehicle A vehicle entry / exit management device for a parking lot comprising:

10. A gate machine having a bar for entry and exit, An outward-facing camera provided near the gate machine for acquiring a front image of a first vehicle for entry towards the bar and a rear image of a second vehicle for exit moving away from the bar, An inward-facing camera provided near the gate machine for acquiring a rear image of the first vehicle moving away from the bar and a front image of the second vehicle heading towards the bar A parking lot comprising: When the first vehicle enters the warehouse, First vehicle front image extraction means for extracting first vehicle front image data of the first vehicle from the image of the outward-facing camera, First vehicle number acquisition means for acquiring the first vehicle number of the first vehicle after extracting the first vehicle front image data, After acquiring the first vehicle number, a first bar raising means for raising the bar; After the bar is raised by the first bar raising means, a first rear vehicle image extraction means for extracting first rear vehicle image data of the first vehicle from the image of the inward-facing camera; After acquiring the first rear vehicle image data, a first bar lowering means for lowering the bar; After extracting the first rear vehicle image data at the time of storing the first vehicle, a management order creation start means for starting the creation of a management order for the first vehicle comprising; At the time of shipping out the second vehicle, A second front vehicle image extraction means for extracting second front vehicle image data of the second vehicle from the image of the inward-facing camera; After extracting the second front vehicle image data, a second vehicle number acquisition means for acquiring the second vehicle number of the second vehicle; After acquiring the second vehicle number, a second bar raising means for raising the bar; After the bar is raised by the second bar raising means, a second rear vehicle image extraction means for extracting second rear vehicle image data of the second vehicle from the image of the outward-facing camera; After acquiring the second rear vehicle image data, a second bar lowering means for lowering the bar A vehicle in-out management device for a parking lot comprising.

11. The front vehicle image extraction means The vehicle in-out management device for a parking lot according to claim 9, comprising a vehicle front image estimation extraction means for estimating and extracting the vehicle front image data by using a learned vehicle front learning control model with the learning vehicle front image data as input data and the image of the vehicle front camera as input data.

12. The first front vehicle image extraction means or the second front vehicle image extraction means Using the learned vehicle front learning control model with the vehicle front image data for learning as input data, the vehicle front image estimation and extraction means for estimating and extracting the first vehicle front image data or the second vehicle rear image data using the image of the outward camera or the inward camera as input data. The vehicle in-out management device for a parking lot according to claim 10.

13. The vehicle rear image extraction means Using the learned vehicle rear learning control model with the vehicle rear image data for learning as input data, the vehicle rear image estimation and extraction means for estimating and extracting the vehicle rear image data using the image of the vehicle rear camera as input data. The vehicle in-out management device for a parking lot according to claim 9.

14. The first vehicle rear image extraction means or the second vehicle rear image extraction means Using the learned vehicle rear learning control model with the vehicle rear image data for learning as input data, the vehicle rear image estimation and extraction means for estimating and extracting the first vehicle rear image data or the second vehicle rear image data using the image of the outward camera or the inward camera as input data. The vehicle in-out management device for a parking lot according to claim 10.

15. Furthermore, after extracting the vehicle rear image data at the time of the vehicle's departure, the vehicle in-out management device for a parking lot according to claim 9, comprising management order creation end means for ending the creation of the management order for the vehicle.

16. Furthermore, after extracting the vehicle rear image data at the time of the second vehicle's departure, the vehicle in-out management device for a parking lot according to claim 10, comprising management order creation end means for ending the creation of the management order for the second vehicle.

Images