Mechanical parking lot

Abstract

To provide a relatively inexpensive mechanical parking lot capable of further relatively checking safety in a getting on / off room at the time of entering / exiting.SOLUTION: In a mechanical parking lot, a vehicle that has entered the getting on / off room can be stored in a parking room. The mechanical parking lot is equipped with an imaging device for imaging the inside of the getting-on / off room, a tracking unit 120 for generating tracking information for associating positions of persons in a plurality of images with each other between the plurality of images imaged by the imaging device and a determination unit 122 that determines whether or not to start a closing operation to close an entering / exiting door opened for entrance / exit based on the tracking information.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] The present invention relates to a mechanical parking lot. [Background technology]

[0002] Mechanical parking lots are known as parking lots that can efficiently park a large number of vehicles in a small space. Mechanical parking lots generally include a boarding / alighting area where drivers can get in and out of their vehicles, a parking space located above or below ground, and a lifting device that moves vehicles between the boarding / alighting area and the parking space. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2006-077425 Summary of the Invention [Problem to be solved by the invention]

[0004] In mechanical parking lots, when closing the entrance / exit door of the loading / de-boarding compartment that has been opened for entry and exit, the safety of the loading / de-boarding compartment, i.e., confirmation that there are no people inside the compartment, is carried out.

[0005] For example, a method of installing a scanner-type laser sensor inside the passenger compartment to check the safety of the compartment can be considered. However, with this method, the vicinity of walls and moving objects such as pallets and vehicles must be excluded from the detection range to prevent false detection, and people outside the detection range cannot be detected.

[0006] Another possible method is to install multiple wide sensors inside the passenger compartment. However, this method requires installing wide sensors nearly all around the passenger compartment to reduce blind spots, which is not practical due to the need to install wide sensors around other devices.

[0007] Another possible method is to install a passive sensor in the passenger compartment to detect a temperature moving object, but this method cannot detect a person standing still in the passenger compartment.

[0008] Another possible method is to install a LiDAR (Light Detection and Ranging, Laser Imaging Detection and Ranging) inside the passenger compartment. However, LiDAR is expensive and has a cost disadvantage.

[0009] The present invention has been made in consideration of these circumstances, and one exemplary purpose of one aspect of the present invention is to provide a relatively inexpensive mechanical parking lot that can more reliably confirm the safety of the boarding and disembarking compartment when entering and exiting the parking lot. [Means for solving the problem]

[0010] In order to solve the above problems, one embodiment of the mechanical parking lot of the present invention is a mechanical parking lot that can store a vehicle that has entered the loading / unloading area in a parking space, and is equipped with an imaging device that captures images of the inside of the loading / unloading area, a tracking unit that generates tracking information that matches the positions of people in multiple images captured by the imaging device, and a judgment unit that judges whether or not to start the closing operation to close the loading / unloading door that has been opened for loading and unloading based on the tracking information.

[0011] Any combination of the above components, or mutual substitution of the components or expressions of the present invention between methods, devices, systems, etc., are also valid aspects of the present invention. [Effects of the Invention]

[0012] According to the present invention, a relatively inexpensive mechanical parking lot can be provided that can more reliably confirm the safety of the boarding and disembarking compartment when entering and exiting the parking lot. [Brief explanation of the drawings]

[0013] [Figure 1] 1 is a cross-sectional view of a mechanical parking lot according to a first embodiment. [Figure 2] FIG. 2 is a plan view of the boarding / deboarding compartment of FIG. [Figure 3] FIG. 2 is a block diagram showing the functions and configuration of the control device of FIG. 1. [Figure 4] FIG. 10 is a diagram illustrating a tracking method. [Figure 5] 10A and 10B are diagrams illustrating tracking in the case where at least a part of the imaging area of ​​a moving object crosses the imaging areas of two imaging devices that are different from each other. [Figure 6] FIG. 10 is a diagram illustrating tracking when there is a blind spot. [Figure 7] 10 is a flowchart showing an example of the operation of a mechanical parking lot when entering the parking lot. [Figure 8] 10 is a flowchart showing an example of the operation of a mechanical parking lot when leaving the parking lot. [Figure 9] FIG. 10 is a block diagram showing the functions and configuration of a control device for a mechanical parking lot according to a second embodiment. [Figure 10] 10(a) to 10(c) are diagrams showing the state of warehousing in chronological order. [Figure 11] 11(a) to 11(d) are diagrams showing the state of warehousing in chronological order. [Figure 12] FIG. 10 is a block diagram showing the functions and configuration of a control device according to a third embodiment. [Figure 13] FIG. 10 is a block diagram showing the functions and configuration of a control device according to a fourth embodiment. [Figure 14] 12(a) to 12(c) are diagrams illustrating a method for identifying the presence or absence of differences from a differential image, taking the case of warehousing as an example. [Figure 15] FIG. 10 is a block diagram showing the functions and configuration of a control device according to a fifth embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0014] The present invention will be described below based on preferred embodiments with reference to the drawings. The same or equivalent components, parts, and processes shown in each drawing will be given the same reference numerals, and redundant explanations will be omitted where appropriate. Furthermore, the embodiments are illustrative and do not limit the invention, and all features and combinations thereof described in the embodiments are not necessarily essential to the invention.

[0015] (First embodiment) FIG. 1 is a front view of a mechanical parking lot 10 according to the first embodiment. The mechanical parking lot 10 is an underground mechanical parking lot in which parking spaces are provided in the basement of a building 104 located above ground. Note that the mechanical parking lot 10 may also be an above-ground mechanical parking lot in which parking spaces are provided inside the building 104.

[0016] The mechanical parking lot 10 comprises a B1F parking space 14, which is a parking space on the first basement floor, a B2F parking space 16, which is a parking space on the second basement floor, a B3F parking space 18, which is a parking space on the third basement floor, a plurality of pallets 32, a first transfer device 56, a plurality of second transfer devices 58, a lift frame 88, two or four masts 90 provided as supports along an elevator shaft 96 having an approximately rectangular cross section, an elevator device 94, an operation panel 28 provided outside the boarding and disembarking space 12, and a control device 100 connected to the operation panel 28.

[0017] The mechanical parking lot 10 is a pallet-type parking lot that uses pallets 32. This pallet-type mechanical parking lot 10 is configured to park vehicles in parking spaces by using an elevator device 94 to raise and lower the pallet 32 ​​on which a vehicle such as an automobile 20, a motorcycle 74, or a bicycle is mounted, or by using a first transfer device 56 and a second transfer device 58 to move the pallet in a planar direction.

[0018] A boarding / deboarding room 12 for loading and unloading vehicles into and from the mechanical parking lot 10 is provided within the building 104. The boarding / deboarding room 12 is provided at the upper end of the elevator shaft 96. A communication hole 98 that connects the boarding / deboarding room 12 with the elevator shaft 96 is provided in the boarding / deboarding room 12.

[0019] The elevator shaft 96 is provided along the vertical direction (z direction). The elevator shaft 96 is connected to each of the B1F parking spaces 14, B2F parking spaces 16, and B3F parking spaces 18. At the lower end of the elevator shaft 96, an elevator device 94 is installed that raises and lowers the lift frame 88. For example, four masts 90 are installed at the four corners of the elevator shaft 96.

[0020] The lift frame 88 is supported by four masts 90 so as to be able to move up and down freely, and is raised and lowered along a hoistway 96 by a lifting device 94. A first transfer device 56 is provided on the upper part of the lift frame 88. The lift frame 88, four masts 90, and lifting device 94 can respectively be the lift frame, four masts, and lifting device described in Japanese Patent Application Laid-Open No. 2009-197417, previously filed by the applicant.

[0021] The pallet 32 ​​is a flat member. The vehicle loading surface 32a, which is the upper surface of the pallet 32, is substantially rectangular. The pallets 32 have a uniform size.

[0022] B1F parking room 14, B2F parking room 16, and B3F parking room 18 each include multiple parking spaces. Each parking space is configured to accommodate a pallet 32. A parking space is one parking area (one unit of parking) within the parking room where a vehicle can be parked together with the pallet.

[0023] The first transfer device 56 is provided on top of the lift frame 88 and moves the pallet 32 ​​in the x direction. When there are two masts 90, the first transfer device 56 also moves the pallet 32 ​​in the y direction. The first transfer device 56 moves the pallet between the elevator shaft 96 and each parking space. The second transfer device 58 is provided in each parking space and moves the pallet 32 ​​in the x direction or y direction. The second transfer device 58 moves the pallet between the parking spaces. The conveying device described in Japanese Patent Publication No. 7-29681, previously filed by the applicant, can be applied to the first transfer device 56 and the second transfer device 58.

[0024] The operation panel 28 functions as a user interface for users or staff of the mechanical parking lot 10. The operation panel 28 has a touch panel. The operation panel 28 is connected to the control device 100 and transmits control signals to the control device 100 in response to operations input to the touch panel.

[0025] FIG. 2 is a plan view of the boarding / deboarding space 12 of the mechanical parking lot 10. The boarding / deboarding space 12 is surrounded by walls (sides, ceiling) except for the entrance / exit gate 12a, and an entrance / exit door 26 is provided at the entrance / exit gate 12a. An imaging device 11 is installed inside the boarding / deboarding space 12. The imaging device 11 is a video camera that captures images of the inside of the boarding / deboarding space 12 at a predetermined cycle and generates frame images for each cycle. In this example, only one imaging device 11 is installed, but the number of imaging devices 11 is not particularly limited, and multiple imaging devices 11 may be installed, for example, to reduce blind spots.

[0026] 3 is a block diagram showing the functions and configuration of the control device 100. The control device 100 includes an instruction receiving unit 110, a storage processing unit 112, a shipping processing unit 114, an image acquisition unit 116, a detection unit 118, a tracking unit 120, a determination unit 122, a model storage unit 124, and a tracking information storage unit 126.

[0027] The image acquisition unit 116 acquires frame images from the imaging device 11 at a predetermined imaging speed (for example, 60 frames / second).

[0028] The detection unit 118 detects a person (area of ​​a person) from the frame image acquired by the image acquisition unit 116. In this embodiment, the detection unit 118 realizes the detection of a person by using a person detection model M stored in the model storage unit 124.

[0029] The person detection model M is a trained model generated by machine learning using a large amount of training data including training images of people (parts such as heads, arms, and legs, or the entire body) and labels indicating what is contained in the images. The person detection model M can be trained using various well-known machine learning techniques. An example of machine learning is deep learning. A specific example of deep learning is the backpropagation method using a neural network.

[0030] When the detection unit 118 inputs a frame image captured by the imaging device 11 to the human detection model M, the human detection model M outputs human detection information related to the frame image. Here, the human detection information includes at least information indicating whether a person (including cases where only a part of a person, such as a head, arm, or leg, has been detected) has been detected, and if a person has been detected, may also include the position of the person.

[0031] The detection unit 118 is not limited to detecting using the human detection model M (trained model), and may perform detection using any known algorithm.

[0032] The tracking unit 120 tracks people detected by the detection unit 118 from frame images. Specifically, the tracking unit 120 identifies the same person for people detected in each of a plurality of frame images. The tracking unit 120 associates the position information within the boarding / deboarding cabin 12 in each frame image of people identified as the same person in each frame image with each other, generates tracking information, and stores it in the tracking information storage unit 126. When the detection unit 118 detects multiple people, it tracks each of the multiple people. In this case, multiple pieces of tracking information are stored in the tracking information storage unit 126.

[0033] The detection unit 118 and the tracking unit 120 execute their respective processes each time the image acquisition unit 116 acquires a frame image, for example, when entry or exit is initiated. That is, they detect and track people in the boarding / departure room 12 substantially in real time. To achieve substantially real-time person detection and tracking, the detection unit 118 and the tracking unit 120 may execute their respective processes by thinning out the frame images. Note that the process is not limited to substantially real-time person detection and tracking, and may be executed collectively, for example, when the determination unit 122 makes a determination as described below.

[0034] The instruction receiving unit 110 receives an instruction (signal) sent from the operation panel .

[0035] When a vehicle is to be parked, the driver or attendant parks the vehicle to be parked outside the boarding / de-boarding compartment 12, gets out of the vehicle, and inputs a command to start warehousing into the operation panel 28. When the operation panel 28 receives the command to start warehousing, it generates a warehousing start signal and sends it to the control device 100. When the command receiving unit 110 receives the warehousing start signal, the warehousing processing unit 112 controls the lifting device 94, the first transfer device 56, and the second transfer device 58 to move an empty pallet to the boarding / de-boarding compartment 12, and further controls a door opening / closing mechanism (not shown) to open the loading / unloading door 26. The warehousing processing unit 112 guides the vehicle to be parked to a parking position on the pallet 32 ​​arranged in the boarding / de-boarding compartment 12 by voice and vehicle guide lights.

[0036] After the vehicle enters the boarding / alighting compartment 12 and stops on the pallet, the driver or attendant gets off the vehicle and inputs a command to start storage into the operation panel 28. When the operation panel 28 receives the command to start storage, it generates a storage request signal and transmits it to the control device 100.

[0037] When the instruction receiving unit 110 receives the storage request signal, the determining unit 122 determines whether or not to start the closing operation of the storage / retrieval door 26 based on the tracking information stored in the tracking information storage unit 126 .

[0038] When all of the tracking information indicates that a person has left the loading / unloading room 12, the determination unit 122 determines that there is no person in the loading / unloading room 12 and therefore it is "possible" to start the closing operation of the loading / unloading door 26. "Tracking information indicates that a person has left the loading / unloading room 12" may mean, for example, a case where the last position information in time series of position information included in the tracking information indicates the outside of the loading / unloading door 12a, or a case where the last position information in time series of position information included in the tracking information indicates the vicinity of the loading / unloading door 12a within the loading / unloading room 12 is discontinued.

[0039] If any of the tracking information indicates that a person is in the boarding / deboarding room 12, the judgment unit 122 judges that it is "impossible" to start the closing operation of the loading / unloading door 26 because there is a person in the boarding / deboarding room 12.

[0040] If the determination result by the determination unit 122 is "possible," the storage processing unit 112 controls the door opening / closing mechanism to close the loading / unloading door 26, and further controls the lifting device 94, the first transfer device 56, and the second transfer device 58 to move the pallet on which the vehicle is loaded from the boarding / unloading room 12 to a predetermined parking space. If the determination result by the determination unit 122 is "not possible," the storage processing unit 112 displays an error on the touch panel of the operation panel 28 without closing the loading / unloading door 26 or moving the pallet 32.

[0041] When a vehicle leaves the garage, the driver or attendant inputs a vehicle ID that identifies the vehicle to be removed into the operation panel 28. The operation panel 28 generates an extraction start signal that includes the input vehicle ID and transmits it to the control device 100. When the instruction receiving unit 110 receives the extraction start signal, the extraction processing unit 114 controls the lifting device 94, the first transfer device 56, and the second transfer device 58 to move the pallet on which the vehicle identified by the vehicle ID included in the extraction start signal is mounted from the parking space to the boarding / deboarding room 12, and controls the door opening / closing mechanism to open the entrance / exit door 26.

[0042] The driver or attendant takes the vehicle out of the boarding / alighting compartment 12, parks the vehicle outside the boarding / alighting compartment 12, and inputs an instruction to complete leaving the parking lot to the operation panel 28. Upon receiving the instruction to complete leaving the parking lot, the operation panel 28 generates a door close request signal and transmits it to the control device 100.

[0043] When the instruction receiving unit 110 receives the door close request signal, the determination unit 122 determines whether or not it is possible to start the closing operation of the entrance / exit door 26, based on the tracking information stored in the tracking information storage unit 126. If all of the tracking information indicates that a person has left the loading / unloading room 12 or that a person has boarded the vehicle to be unloaded, the determination unit 122 determines that it is "possible" to start the closing operation of the entrance / exit door 26. If any of the tracking information indicates that a person is present in the loading / unloading room 12, the determination unit 122 determines that it is "impossible" to start the closing operation of the entrance / exit door 26.

[0044] If the determination result by the determination unit 122 is "possible," the delivery processing unit 114 controls the door opening / closing mechanism to close the loading / unloading door 26. If the determination result by the determination unit 122 is "impossible," the delivery processing unit 114 displays an error on the touch panel of the operation panel 28 without closing the loading / unloading door 26.

[0045] Next, a more detailed description will be given of tracking by the tracking section 120. Note that tracking by the tracking section 120 is not limited to the method described below, and various known methods can be used.

[0046] 4 is a diagram illustrating an example of a tracking technique. t ,F t+1 ,F t+2 are three frame images that are consecutive in time order. t ,F t+1 ,F t+2 H in t ,H t+1 ,H t+2 is a person detected by the detection unit 118. t ,H t+1 ,H t+2are the same person. Image S is composed of three frame images F t , F t+1 ,F t+2 This is an image superimposed on the original.

[0047] In this example, for ease of understanding, t ,H t+1 ,H t+2 The positions are separated so that the people do not overlap, but the time difference between successive frame images is, for example, 0.1 seconds or less, and the amount of movement of the person during this time is very small. t ,H t+1 ,H t+2 appear to overlap at least partially.

[0048] Below, frame image F t Person H t and frame image F t+1 Person H t+1 are identified as the same person, and frame image F t+2 We will explain how to identify the same person from these. t and H t+1 These pieces of position information are associated with each other and stored as tracking information in the tracking information storage unit 126.

[0049] The tracking unit 120 detects the frame image F t+2 The tracking unit 120 determines the position information of the person detected in the frame image F within the boarding / deboarding room 12. The position information may be, for example, coordinates in an XY coordinate system with the origin at any corner within the boarding / deboarding room 12. t+2 The position information of the person detected in the frame image F is calculated based on, for example, a known image analysis technique. t+2 The position of the feet may also be identified.

[0050] Next, the tracking unit 120 identifies the same person between the frame images based on, for example, the direction of movement. t and people H t+1 About H tFrom the position of t+1 Direction of movement to position D t+1 Next, the tracking unit 120 identifies the person H t+2 About H t+1 From the position of t+2 Direction of movement to position D t+2 The tracking unit 120 identifies the moving direction D t+1 and movement direction D t+2 If the acute angle between the two is equal to or less than a predetermined threshold angle α, the person H t+1 and H t+2 are identified as the same person.

[0051] Furthermore, for example, the tracking unit 120 identifies the same person between frame images based on the amount of movement. t+1 And, human H t+1 and the same candidate, person H t+2 The distance between the t+1 and H t+2 If the amount of movement L is equal to or less than the threshold amount of movement, the tracking unit 120 determines that the person H t+1 and H t+2 The threshold movement amount may be determined based on the frame rate of the image capturing device 11, for example.

[0052] Furthermore, for example, the tracking section 120 may identify the same person between frame images based on both the direction and amount of movement (that is, vector).

[0053] The tracking unit 120 is a t+2 The location information of the person identified as the same person H t and people H t+1 The location information is stored in the tracking information storage unit 126 in association with the location information.

[0054] 5 is a diagram illustrating tracking in the case where the object moves from the imaging area of ​​one imaging device 11 to the imaging area of ​​the other imaging device 11 so as to straddle the imaging areas of two imaging devices 11 whose imaging areas are at least partially different from each other. Here, it is assumed that the imaging areas of the two imaging devices 11 are entirely different from each other (i.e., do not overlap).

[0055] Frame image F1 i (i=t, t+1, t+2) is a frame image captured by one of the two image capture devices 11, and F2 i is a frame image captured by the other of the two imaging devices 11. Frame image F1 t ,F1 t+1 ,F1 t+2 are three frame images that are consecutive in time order. Frame image F2 t ,F2 t+1 ,F2 t+2 are three frame images that are consecutive in time order. Frame image F1 i and frame image F2 i are frame images captured at substantially the same time.

[0056] Image S1 is a set of three frame images F1 t ,F1 t+1 ,F1 t+2 Image S2 is an image created by superimposing three frame images F2 t ,F2 t+1 ,F2 t+2 The frame image F1 t Based on H1 t and frame image F1 t+1 Based on H1 t+1 and are identified as the same person.

[0057] Identifying the same person when the image capture area is crossed is basically the same as identifying the same person when the image capture area is not crossed, and can be done from at least one of the direction of movement and the amount of movement.

[0058] For example, when identifying the same person based on the movement direction, the tracking unit 120 t+1 Person H1 t+1 and person H2 in frame image F2, who is a candidate for the same person. t+2 About H1 t+1 From position H1 t+2 Direction of movement to position D t+2 The tracking unit 120 identifies the moving direction D t+1 and movement direction D t+2 If the acute angle between the two is less than a predetermined threshold angle, t+1 and H t+2 are identified as the same person.

[0059] Furthermore, when identifying the same person based on the amount of movement, the tracking unit 120 t+1 Person H1 t+1 and person H2 in frame image F2, who is a candidate for the same person. t+2 The distance between the person H1 and the person H2 is t+1 and people H2 t+2 If the amount of movement is equal to or less than the threshold amount of movement, the tracking unit 120 identifies the person H1 t+1 and people H2 t+2 are identified as the same person.

[0060] In this way, by identifying the same person when the person moves across two non-overlapping imaging areas, the same person can be identified with a relatively high degree of accuracy.

[0061] 6 is a diagram illustrating tracking when there is a blind spot. Here, a case where two image capturing devices 11_1 and 11_2 are installed in the boarding / deboarding compartment 12 will be described, but the same explanation applies to a case where one image capturing device or three or more image capturing devices are installed.

[0062] FIG. 6 is a plan view of the boarding / deboarding compartment 12. The dashed lines in FIG. 6 indicate the imaging areas of the imaging devices 11_1 and 11_2. The tracking unit 120 divides the interior of the boarding / deboarding compartment 12 into a plurality of areas for management. In this example, the interior of the boarding / deboarding compartment 12 is divided into areas A11 to A55 for management. Consider a case where a person who was detected in the frame images of either the imaging device 11_1 or the imaging device 11_2 is lost, that is, the person moves out of the imaging areas of both the imaging device 11_1 and the imaging device 11_2 and is no longer detected in any of the frame images. In this case, the tracking unit 120 estimates the area where the person is located based on the position information and movement direction of the person in the frame image before the person was lost (for example, just before the person was lost). In the illustrated example, the tracking unit 120 estimates that the person is in area A33 (a blind spot) based on the position information and movement direction when the person was in area A24. Then, when a person is detected in an area near (for example, adjacent to) the estimated area, the tracking unit 120 identifies that person as the same person who was previously lost sight of.

[0063] Next, the operation of the mechanical parking lot 10 configured as above will be explained.

[0064] FIG. 7 is a flowchart showing an example of the operation of the mechanical parking lot 10 when entering a vehicle. The driver or attendant stops the vehicle to be entered in front of the entrance / exit door 26. The driver or attendant inputs an entry start command into the operation panel 28. The operation panel 28 receives the entry start command (S10). The detection unit 118 and tracking unit 120 start person detection and tracking based on the frame image (S12). The entry processing unit 112 places an empty pallet in the boarding / de-boarding compartment 12 (S14), opens the entrance / exit door 26 (S16), and guides the vehicle to the pallet 32 ​​inside the boarding / de-boarding compartment 12 (S18).

[0065] The driver or attendant parks the vehicle on the pallet 32. After confirming that there is no one in the boarding / deboarding compartment 12, the driver or attendant inputs a storage start command to the operation panel 28. The operation panel 28 receives the storage start command (S20). The determination unit 122 determines whether or not it is possible to start the closing operation of the loading / unloading door 26 based on the tracking information stored in the tracking information storage unit 126 (S22). If the determination result is "not possible" (N in S22), an error is displayed on the touch panel of the operation panel 28, for example, and the process returns to S20. If the determination result is "possible" (Y in S22), the warehousing processing unit 112 closes the loading / unloading door 26 (S24) and moves the pallet 32 ​​on which the vehicle is loaded to a parking space (S26). The detection unit 118 and tracking unit 120 end person detection and tracking (S28).

[0066] 8 is a flowchart showing an example of the operation of the mechanical parking lot 10 when the vehicle is leaving the parking lot. The driver or attendant inputs a leaving start command to the operation panel 28. The operation panel 28 receives the leaving start command (S40). The detection unit 118 and the tracking unit 120 start detecting and tracking people based on the frame image (S42). The leaving processing unit 114 moves the pallet 32 ​​loaded with the vehicle identified by the management number included in the leaving start command from the parking space to the boarding / deboarding space 12 (S44), opens the entrance / exit door 26 (S46), and guides the vehicle out of the boarding / deboarding space 12 (S48).

[0067] The driver or attendant drives the vehicle out of the loading / unloading compartment 12 and parks it outside the loading / unloading compartment 12. After confirming that no one is inside the loading / unloading compartment 12, the driver or attendant inputs a door close command to the operation panel 28. The operation panel 28 receives the door close command (S50). The determination unit 122 determines whether or not the closing operation of the loading / unloading door 26 can be started based on the tracking information stored in the tracking information storage unit 126 (S52). If the determination result is "not possible" (N in S52), an error is displayed on the touch panel of the operation panel 28, for example, and the process returns to S50. If the determination result is "possible" (Y in S52), the unloading processing unit 114 closes the loading / unloading door 26 (S54), and the detection unit 118 and tracking unit 120 end person detection and tracking (S56).

[0068] 7 and 8 are merely examples, and it is possible to add other processes, delete some processes, or change the order of processes.

[0069] Next, the effects of this embodiment will be described. According to this embodiment, the presence or absence of a person in the boarding / deboarding compartment 12, and therefore whether or not to start the closing operation of the loading / unloading door 26 opened for entry and exit, are determined based on tracking information of the detected person. For example, even if there is a blind spot within the boarding / deboarding compartment 12 and a person who was once detected moves into that blind spot and is no longer detected even though they have not yet left the boarding / deboarding compartment 12, it can be determined based on the tracking information that there is a person in the boarding / deboarding compartment 12 and therefore the closing operation cannot be started. In other words, according to this embodiment, it is possible to more reliably determine the presence or absence of a person in the boarding / deboarding compartment 12 and therefore whether or not to start the closing operation. In other words, it is possible to more reliably confirm the safety within the boarding / deboarding compartment 12 when entering or exiting. Furthermore, because no expensive sensors are required, this can be implemented relatively inexpensively.

[0070] Furthermore, according to this embodiment, people in the boarding / deboarding compartment 12 are detected based on the image captured by the imaging device 11. This allows detection in three-dimensional space, rather than two-dimensionally as with scanner-type laser sensors or wide sensors, so a three-dimensional detection area is formed, making it possible to minimize blind spots in detection. Furthermore, it is possible to detect stationary people that passive sensors cannot detect, and it is possible to detect people of all ages, postures, and movements, including infants and people lying down.

[0071] (Second embodiment) In the second embodiment, the presence or absence of people in the boarding / deboarding compartment and therefore whether or not to start the closing operation are determined by counting the number of people getting off or getting on the vehicle in the boarding / deboarding compartment and the number of people entering and leaving the boarding / deboarding compartment. The following mainly describes the differences from the first embodiment.

[0072] 9 is a block diagram showing the functions and configuration of a control device 200 according to the second embodiment. The control device 200 includes an instruction receiving unit 110, a storage processing unit 112, a delivery processing unit 114, an image acquiring unit 116, a detecting unit 118, a determining unit 222, a people counting unit 228, a model storing unit 124, and a people number storing unit 229.

[0073] The number of people counter 228 includes an alighting number of people counter 230, an getting on number of people counter 232, an entering number of people counter 234, and an exiting number of people counter 236.

[0074] The alighting person counting unit 230 counts the number of people (hereinafter referred to as "alighting person") who have alighted from a vehicle parked in the boarding / alighting compartment 12 when the vehicle enters the parking lot. Specifically, the alighting person counting unit 230 counts up the alighting person number when it is determined that a person detected by the detection unit 118 has alighted (come out) from the vehicle based on a known image analysis technique for a frame image. Note that, for example, it is also conceivable that a person who alights from a vehicle may get on a vehicle and then get off the vehicle again. Taking such cases into consideration, the alighting person counting unit 230 counts down the alighting person number when it is determined that a person has alighted from the vehicle.

[0075] The passenger number counting unit 232 counts the number of people (hereinafter referred to as "passenger number") who board a vehicle parked in the boarding / alighting compartment 12 when the vehicle leaves the parking lot. More specifically, the passenger number counting unit 232 counts up the number of passengers when it is determined that a person detected by the detection unit 118 has boarded (entered) the vehicle based on a known image analysis technique for a frame image. Note that, for example, it is possible that a person who boarded the vehicle gets off the vehicle and then gets on again. Taking such cases into consideration, the passenger number counting unit 232 counts down the number of passengers when it is determined that a person has boarded the vehicle.

[0076] For example, when a person suddenly appears near the vehicle (i.e., is detected by the detection unit 118) while the door of the vehicle parked in the boarding / deboarding compartment 12 is open, the alighting number of people counting unit 230 and the boarding number of people counting unit 232 may determine that the person has alighted from the vehicle. Also, when a person suddenly disappears near the vehicle (i.e., is no longer detected by the detection unit 118) while the door of the vehicle parked in the boarding / deboarding compartment 12 is open, the alighting number of people counting unit 230 and the boarding number of people counting unit 232 may determine that the person has alighted from the vehicle.

[0077] The entry number counting unit 234 counts the number of people who walk into the boarding / alighting room 12 (hereinafter referred to as "entering number of people") when entering and leaving the room. In detail, when it is determined that the person detected by the detection unit 118 walked into the boarding / alighting room 12 based on a known image analysis technique for the frame image, the entry number counting unit 234 counts up the number of people who have walked into the boarding / alighting room 12.

[0078] The exiting person counting unit 236 counts the number of people who walk out of the boarding / alighting room 12 when entering and leaving the room (hereinafter referred to as the "number of people leaving the room"). In detail, when it is determined that a person detected by the detection unit 118 has walked into the boarding / alighting room 12 based on a known image analysis technique for a frame image, the exiting person counting unit 236 counts up the number of people leaving the room.

[0079] In addition, if there are multiple entrances and exits through which people can enter and exit the room, such as when there are multiple entrances and exits or when there is an emergency exit in addition to the entrances and exits, the entering person counting unit 234 counts the number of people entering the room from all of those entrances and exits, and the leaving person counting unit 236 counts the number of people leaving the room from all of those entrances and exits.

[0080] The numbers of people counted by the alighting person counting unit 230, the boarding person counting unit 232, the entering person counting unit 234, and the leaving person counting unit 236 are stored in a number-of-people memory unit 237.

[0081] The number of people counted by the people counting unit 228 can be summarized as follows. (1) When entering the parking lot, the alighting person counting unit 230, the entering person counting unit 234, and the leaving person counting unit 236 count the number of people alighting, entering, and leaving, respectively. (2) When leaving the parking lot, the passenger counting unit 232, the entering passenger counting unit 234, and the leaving passenger counting unit 236 count the number of passengers, the number of entering passengers, and the number of leaving passengers, respectively.

[0082] For example, when entry or exit from the vehicle is initiated, the detection unit 118 and the people counting unit 228 execute their respective processes each time the image acquisition unit 116 acquires a frame image. That is, they detect and count people in the boarding / departure compartment 12 substantially in real time. To achieve substantially real-time person detection and people counting, the detection unit 118 and the people counting unit 228 may execute their respective processes by thinning out the frame images. Note that the process is not limited to substantially real-time person detection and people counting, and may be executed all at once when the determination unit 122 makes a determination, for example.

[0083] When entering the vehicle, if the following formula (1) is satisfied, the judgment unit 222 judges that there is no person in the boarding / deboarding room 12 and therefore it is possible to start the closing operation of the loading / unloading door 26, and if the following formula is not satisfied, it judges that there is a person in the boarding / deboarding room 12 and therefore it is not possible to start the closing operation of the loading / unloading door 26. (Number of people getting off) + (Number of people entering) = (Number of people leaving) (1)

[0084] 10(a) to 10(c) are diagrams showing the situation at the time of parking in chronological order. In FIG. 10(a), four people who entered the boarding / alighting compartment 12 while still aboard the vehicle get off, and one person walks into the boarding / alighting compartment 12. In FIG. 10(b), three people leave the boarding / alighting compartment 12, and two people still remain in the boarding / alighting compartment 12. In FIG. 10(c), all five people leave the boarding / alighting compartment 12, and no one remains in the boarding / alighting compartment 12.

[0085] At the timing of FIG. 10(b), the number of people getting off is 4, the number of people entering is 1, and the number of people leaving is 3, so formula (1) does not hold. Therefore, at the timing of FIG. 10(b), the judgment unit 222 judges that it is not possible to start the closing operation of the entrance / exit door 26. At the timing of FIG. 10(c), the number of people getting off is 4, the number of people entering is 1, and the number of people leaving is 5, so formula (1) holds. Therefore, at the timing of FIG. 10(c), the judgment unit 222 judges that it is possible to start the closing operation of the entrance / exit door 26.

[0086] Returning to Figure 9, when the vehicle leaves the depot, if the following formula (2) is satisfied, the judgment unit 222 judges that there is no person in the boarding / deboarding room 12 and therefore it is possible to start the closing operation of the loading / unloading door 26, and if the following formula is not satisfied, it judges that there is a person in the boarding / deboarding room 12 and therefore it is not possible to start the closing operation of the loading / unloading door 26. (Number of people entering) = (Number of people getting on) + (Number of people leaving) (2)

[0087] 11(a) to 11(d) are diagrams showing the situation at the time of leaving the parking lot in chronological order. In FIG. 11(a), five people enter the boarding / deboarding compartment 12, and four of them get on the vehicle. In FIG. 11(b), the vehicle carrying four people leaves the boarding / deboarding compartment 12, and one person still remains in the boarding / deboarding compartment 12. In FIG. 11(d), the last person leaves the boarding / deboarding compartment, and no one remains in the boarding / deboarding compartment 12.

[0088] At the timing in FIG. 11(c), the number of people entering the room is 5, the number of people getting on is 4, and the number of people leaving is 0, so formula (2) does not hold. Therefore, at the timing in FIG. 11(c), the determination unit 222 determines that the closing operation cannot be started. In the example in FIG. 11(d), the number of people entering the room is 5, the number of people getting on is 4, and the number of people leaving is 1, so formula (2) holds. Therefore, at the timing in FIG. 11(d), the determination unit 222 determines that the closing operation can be started.

[0089] The operation when entering a mechanical parking lot in this embodiment is basically the same as the operation when entering in the first embodiment, and in the flowchart of Figure 7, "start of person detection and tracking" in S12 should be read as "start of person detection and people counting", and "end of person detection and tracking" in S28 should be read as "end of person detection and people counting".

[0090] The operation when exiting the mechanical parking lot in this embodiment is basically the same as the operation when exiting in the first embodiment, and it is sufficient to read "start of person detection and tracking" in S42 of the flowchart in Figure 8 as "start of person detection and people counting", and "end of person detection and tracking" in S56 as "end of person detection and people counting".

[0091] Next, the effects of this embodiment will be described. According to this embodiment, the presence or absence of a person in the boarding / deboarding compartment 12, and therefore whether or not to start the closing operation of the loading / unloading door 26 opened for entry and exit, are determined based on the number of people getting off or on, and the number of people entering and leaving. For example, even if there is a blind spot within the boarding / deboarding compartment 12 and a person who was once detected moves into that blind spot and is no longer detected even though they have not yet left the boarding / deboarding compartment 12, it can be determined that there is a person in the boarding / deboarding compartment 12 and therefore the closing operation cannot be started based on the count results of the number of people. In other words, this embodiment can more reliably determine the presence or absence of a person in the boarding / deboarding compartment 12 and therefore whether or not to start the closing operation. In other words, it is possible to more reliably confirm the safety of the boarding / deboarding compartment 12 when entering or exiting. Furthermore, because no expensive sensors are required, this can be implemented relatively inexpensively.

[0092] Consider a case where the number of people inside the vehicle is counted from an image of the vehicle instead of the number of people getting off or the number of people getting on, and the presence or absence of people in the boarding / deboarding compartment 12 is determined based on the number of people inside the vehicle and the number of people entering and leaving. In this case, for example, if a person inside the vehicle is in a blind spot other than the window, such as the vehicle housing, or if the windows are treated in a way that provides high visibility from the inside but low visibility from the outside, there is a risk of the number of people not being counted, and as a result, there is a risk of not being able to correctly determine the presence or absence of people in the boarding / deboarding compartment 12. In contrast, according to this embodiment, the presence or absence of people in the boarding / deboarding compartment 12 is determined based on the number of people getting off or the number of people getting on, which is not likely to result in a missed count, so that safety in the boarding / deboarding compartment 12 can be more reliably confirmed when entering or leaving the parking lot.

[0093] (Third embodiment) In the third embodiment, an ID is assigned to a person detected in the boarding / deboarding compartment. When entering the parking lot, the presence or absence of a person in the boarding / deboarding compartment and therefore whether or not to start the closing operation are determined based on whether or not the person to whom the ID was assigned has left the compartment. When leaving the parking lot, the presence or absence of a person in the boarding / deboarding compartment and therefore whether or not to start the closing operation are determined based on whether or not the person to whom the ID was assigned has left the compartment or entered the vehicle. The following mainly describes the differences from the first embodiment.

[0094] 12 is a block diagram showing the functions and configuration of a control device 300 according to the third embodiment. The control device 300 includes an instruction receiving unit 110, a storage processing unit 112, a delivery processing unit 114, an image acquiring unit 116, a detecting unit 118, a determining unit 322, a feature extracting unit 338, an ID assigning unit 340, an updating unit 342, and a feature storing unit 344.

[0095] The feature extraction unit 338 extracts features of the person detected by the detection unit 118 from the frame image. The extracted features include, for example, bone structure, facial shape, clothing, etc. The feature extraction unit 338 only needs to extract features that can uniquely identify a person, and may extract one type of feature or multiple types of features. For example, the feature extraction unit 338 may extract only bone structure information, or may extract bone structure information and clothing information.

[0096] The ID assigning unit 340 assigns an ID to the person detected by the detection unit 118. Specifically, the ID assigning unit 340 stores the features extracted by the feature extraction unit 338 in the feature storage unit 344. Because the feature information itself is unique data, the feature information itself may be treated as an ID and only the feature information may be stored in the feature storage unit, or the feature information may be associated with a unique ID (e.g., ID001, ID002, ...) and stored in the feature storage unit 344. If the features of the person detected by the detection unit 118 and extracted by the feature extraction unit 338 are the same as the features stored in the feature storage unit 344, it means that an ID has already been assigned to that person. In this case, a new ID is not assigned. In other words, the extracted features are not stored in the feature storage unit 344.

[0097] When a vehicle enters the warehouse, the update unit 342 determines, based on known image analysis techniques for the frame image, that the person detected by the detection unit 118 has left the room, and then deletes the person's characteristic information from the characteristic memory unit 344.

[0098] When the vehicle leaves the garage, the update unit 342 determines, based on known image analysis technology for the frame image, that the person detected by the detection unit 118 has entered or left the vehicle, and then deletes the person's characteristic information from the characteristic memory unit 344.

[0099] The detection unit 118, the feature extraction unit 338, the ID assignment unit 340, and the update unit 342 execute their respective processes each time the image acquisition unit 116 acquires a frame image, for example, when entry or exit is initiated. That is, they detect people in the boarding / departure room 12, extract their features, and assign or delete IDs in substantially real time. The detection unit 118, the feature extraction unit 338, the ID assignment unit 340, and the update unit 342 may execute their respective processes by thinning out frame images to achieve substantially real-time person detection and headcount. Note that the detection unit 118, the feature extraction unit 338, the ID assignment unit 340, and the update unit 342 are not limited to executing their processes substantially in real time, and may execute their processes collectively, for example, when the determination unit 122 makes a determination.

[0100] When entering the vehicle, if all people assigned IDs have left the vehicle, in this example, if there is no record remaining in the memory unit, it means that there is no person in the boarding / deboarding room 12, and therefore the determination unit 322 determines that it is possible to start the closing operation of the loading / unloading door 26. If there is anyone among the people assigned IDs who has not left the vehicle, in this example, if the characteristic information of any person remains in the characteristic memory unit 344, it means that there is someone in the boarding / deboarding room 12, and therefore the determination unit 322 determines that it is not possible to start the closing operation of the loading / unloading door 26.

[0101] When leaving the garage, if all people assigned IDs have either gotten on or left the vehicle, in this example, if there is no characteristic information remaining in the characteristic memory unit 344, it means that there is no person in the boarding / alighting room 12, and therefore the determination unit 322 determines that it is possible to start the closing operation of the entrance / exit door 26. If there is anyone among the people assigned IDs who has not gotten on the vehicle and has not left the room, in this example, if there is characteristic information remaining in the characteristic memory unit 344, it means that there is someone in the boarding / alighting room 12, and therefore it is not possible to start the closing operation of the entrance / exit door 26.

[0102] The operation when entering a mechanical parking lot in this embodiment is basically the same as the operation when entering in the first embodiment, and in the flowchart of Figure 7, "start of person detection and tracking" in S12 should be read as "start of person detection, feature extraction, ID assignment, and ID deletion," and "end of person detection and tracking" in S28 should be read as "end of person detection, feature extraction, ID assignment, and ID deletion."

[0103] The operation at the time of exiting the mechanical parking lot in this embodiment is basically the same as the operation at the time of exiting in the first embodiment, and in the flowchart of Figure 8, "start of person detection and tracking" in S42 should be read as "start of person detection, feature extraction, ID assignment, and ID deletion," and "end of person detection and tracking" in S56 should be read as "end of person detection, feature extraction, ID assignment, and ID deletion."

[0104] According to this embodiment, it is possible to achieve the same effects as those of the first embodiment.

[0105] (Fourth embodiment) In the fourth embodiment, the presence or absence of a person in the boarding / deboarding compartment and therefore whether or not to start the closing operation of the loading / unloading door are determined by comparing a predetermined reference image of the boarding / deboarding compartment with an image of the interior of the compartment at the time of determination. The following will mainly explain the differences from the first embodiment.

[0106] 13 is a block diagram showing the functions and configuration of a control device 400 according to the fourth embodiment. The control device 100 includes an instruction receiving unit 110, a storage processing unit 112, a delivery processing unit 114, an image acquisition unit 116, and a determination unit 422.

[0107] The determination unit 422 compares a reference image (described later) of the inside of the boarding / deboarding room 12 with an image of the inside of the boarding / deboarding room 12 at the time of the determination (hereinafter referred to as the "determination image"), and identifies whether or not there is a difference. If there is no difference between the two, the determination unit 422 determines that there is no person in the boarding / deboarding room 12 and therefore it is possible to start the closing operation of the loading / unloading door 26. If there is a difference between the two, the determination unit 422 determines that there may be a person in the boarding / deboarding room 12 and therefore it is not possible to start the closing operation of the loading / unloading door 26.

[0108] The reference image at the time of warehousing is an image captured inside the boarding / de-boarding room 12 when the vehicle to be warehousing is parked on a pallet 32 ​​arranged inside the boarding / de-boarding room 12 and there is no one in the boarding / de-boarding room 12 except for the person inside the vehicle to be warehousing. The reference image at the time of warehousing is, for example, an image captured inside the boarding / de-boarding room 12 when the vehicle is guided into the boarding / de-boarding room 12 and parked at the parking position on the pallet 32.

[0109] The reference image at the time of leaving the parking lot is an image captured of the inside of the boarding / de-boarding room 12 in a state where an empty pallet 32 ​​is placed in the boarding / de-boarding room 12 and there are no vehicles or people inside the boarding / de-boarding room 12. The reference image at the time of leaving the parking lot may be, for example, an image prepared in advance.

[0110] The determination unit 422 may determine whether or not there is a difference from a differential image obtained by taking the difference between the determination image and the initial image. FIGS. 14(a) to 14(c) are diagrams illustrating a method for determining whether or not there is a difference from a differential image, using the case of entering a warehouse as an example. FIG. 14(a) shows a reference image. FIG. 14(b) shows a determination image. In the determination image of FIG. 14(b), there is a person in the boarding / deboarding compartment 12. FIG. 14(c) shows a differential image obtained by taking the difference between the determination image and the reference image. If there is a difference between the reference image and the determination image, a different portion remains in the differential image, as shown in FIG. 14(c). The determination unit 422 may determine whether or not there is a difference from the presence or absence of this different portion.

[0111] According to this embodiment, it is possible to achieve the same effects as those of the first embodiment.

[0112] (Fifth embodiment) In the fifth embodiment, a trained model is used that is trained to output information regarding whether or not the closing operation of the loading / unloading door can be started when an image of the inside of the loading / unloading compartment is input. The following mainly describes the differences from the first embodiment.

[0113] 15 is a block diagram showing the functions and configuration of a control device 500 according to the fifth embodiment. The control device 500 includes an instruction receiving unit 110, a storage processing unit 112, a delivery processing unit 114, an image acquiring unit 116, a determination unit 522, and a model storage unit 546.

[0114] The model storage unit 546 stores an entry model M1 and an exit model M2.

[0115] The entry model M1 is a trained model generated by machine learning using multiple pieces of training data including captured images of the interior of the loading / unloading compartment 12 when the vehicle is parked at a predetermined stopping position on a pallet 32 ​​arranged in the loading / unloading compartment 12, and labels indicating the presence or absence of a person in the captured images (in other words, whether or not a person is captured in the captured images). The entry model M1 receives as input captured images of the interior of the loading / unloading compartment 12 when the vehicle is parked at a predetermined stopping position. The entry model M1 outputs a determination result as to whether or not a person is present in the loading / unloading compartment 12.

[0116] The model M2 at the time of leaving is a trained model generated by machine learning using multiple pieces of training data including captured images of the inside of the boarding / de-boarding space 12 with an empty pallet 32 ​​placed therein and labels indicating the presence or absence of a person in the captured images. The model M2 at the time of leaving is input with captured images of the inside of the boarding / de-boarding space 12 with an empty pallet 32 ​​placed therein (no vehicle parked). The model M2 at the time of leaving outputs a determination result as to the presence or absence of a person in the boarding / de-boarding space 12.

[0117] At the time of entering the warehouse, the determination unit 522 uses the entry-time model M1 stored in the model storage unit 546 to determine whether or not to start the closing operation of the loading / unloading door 26. Specifically, an image of the inside of the boarding / unloading room 12 at the timing when it is desired to determine whether or not to start the closing operation of the loading / unloading door 26 (for example, the timing when the instruction receiving unit 110 receives a storage request signal) is input to the entry-time model M1. The determination unit 522 acquires the determination result output from the entry-time model M1. If the determination result indicates that there is no person in the boarding / unloading room 12, the determination unit 522 determines that it is possible to start the closing operation of the loading / unloading door 26. If the determination result indicates that there is a person in the boarding / unloading room 12, the determination unit 522 determines that it is not possible to start the closing operation of the loading / unloading door 26.

[0118] At the time of leaving the warehouse, the determination unit 522 determines whether or not to start the closing operation of the entrance / exit door 26, using the exit model M2 stored in the model storage unit 546. Specifically, a captured image of the inside of the boarding / de-boarding compartment 12 at the timing when it is desired to determine whether or not to start the closing operation of the entrance / exit door 26 (for example, the timing when the instruction receiving unit 110 receives a door close request signal) is input to the exit model M2. The determination unit 522 acquires the determination result of the presence or absence of a person in the boarding / de-boarding compartment 12 output from the exit model M2. If the determination result of the presence or absence of a person output from the exit model M2 indicates that no person is present in the boarding / de-boarding compartment 12, the determination unit 522 determines that it is possible to start the closing operation of the entrance / exit door 26, and if the determination result indicates that a person is present in the boarding / de-boarding compartment 12, the determination unit 522 determines that it is not possible to start the closing operation of the entrance / exit door 26.

[0119] The entry model M1 and the exit model M2 may be trained to determine whether or not to start the closing operation of the entrance / exit door 26. In this case, the determination unit 522 may use the determination results of the entry model M1 and the exit model M2 as the determination result of whether or not to start the closing operation of the entrance / exit door 26.

[0120] According to this embodiment, a learning model is used to determine whether or not there is a person in the boarding / deboarding compartment 12, and therefore whether or not the closing operation of the entrance / exit door 26 can be started, so that the accuracy of the determination is high.

[0121] The configuration and operation of the mechanical parking system according to the embodiment have been described above. This embodiment is merely an example, and it will be understood by those skilled in the art that various modifications are possible in the combination of the components, and that such modifications are also within the scope of the present invention.

[0122] (Variation 1) The first embodiment and the second embodiment may be combined. In this case, the number of people getting off, getting on, entering, and leaving the vehicle may be counted based on tracking information. According to this modification, these numbers can be counted more accurately.

[0123] (Variation 2) The first embodiment and the third embodiment may be combined. In this case, it is possible to more accurately identify whether or not people detected between frame images are the same person. For example, even when a person moves across the imaging areas of two imaging devices 11, at least a part of which is different from each other, it is possible to more accurately identify whether or not they are the same person. In other words, this modification allows for more accurate tracking.

[0124] (Variation 3) The second embodiment and the third embodiment may be combined. In this case, since an ID is assigned to each person to be counted, it is possible to prevent the same person from being counted twice. According to this modification, it is possible to count the number of people more accurately.

[0125] (Variation 4) The possibility of starting the closing operation of the loading / unloading door 26 that has been opened for loading / unloading may be determined by each of any two or more of the methods of the first to fifth embodiments. In this case, for example, if the determination results of all the methods are "possible," the start of the closing operation of the loading / unloading door 26 may be determined to be "possible."

[0126] (Variation 5) When it is determined that the closing operation of the loading / unloading door 26 that was opened for loading / unloading is "possible," the loading / unloading processing unit 112 and the unloading processing unit 114 may automatically close the loading / unloading door 26 without waiting for an instruction from the driver or attendant. In this case, the burden on the driver or attendant is reduced. Also, the loading / unloading door 26 will not be forgotten to be closed.

[0127] (Variation 6) Unlike the embodiment, a person in the boarding / deboarding compartment 12 may be detected even after the entrance / exit door 26 is closed. For example, a person may be detected at all times. In this case, the control device may notify the parking lot management office, the parking lot service center, or the like that a person has been detected.

[0128] (Variation 7) In the embodiment and the above-described modified example, the case where the starting of the closing operation of the loading / unloading door 26 that has been opened for entering or exiting the loading / unloading compartment 12 is prohibited when a person is present in the loading / unloading compartment 12 has been described. However, animals such as dogs and cats or external objects may be treated in the same way as people. In other words, the starting of the closing operation of the loading / unloading door 26 may also be prohibited when an animal or external object is present in the loading / unloading compartment 12.

[0129] (Variation 8) In the above-described embodiment and modified example, the mechanical parking lot is a pallet-type parking lot that uses pallets, but this is not limited to this. The mechanical parking lot may be, for example, a parking lot that does not use pallets, such as a slat conveyor type, or a system in which vehicles are transferred to elevators or storage shelves by the passing of comb teeth. This modified example achieves the same functions and effects as the above-described embodiment and modified example.

[0130] Any combination of the above-described embodiments and modifications is also useful as an embodiment of the present invention. A new embodiment resulting from the combination has the combined effects of the combined embodiments and modifications. [Explanation of symbols]

[0131] 10 Mechanical parking lot, 11 Imaging device, 12 Boarding / exiting room, 26 Entrance / exit door, 30 Control device, 120 Tracking unit, 122,222,322,422,522 Determination unit.

Claims

1. A mechanical parking lot capable of storing a vehicle that has entered a boarding / disembarking area in a parking space, an imaging device that images the interior of the boarding / deboarding compartment; a tracking unit that identifies the same person for each person detected in a plurality of images captured by the imaging device and generates tracking information that associates position information in each image of the person identified as the same person with each other; a determination unit that determines whether or not a closing operation of closing an entrance / exit door of the boarding / de-boarding compartment that has been opened for the purpose of entering or leaving the compartment can be started based on the tracking information, the determination unit determining that the closing operation cannot be started when the tracking information indicates that the person is present in the boarding / de-boarding compartment; Equipped with the tracking unit determines whether a person detected from a first image captured by the imaging device and a person detected from a second image captured by the imaging device temporally later than the first image are the same person based on whether at least one of a direction and an amount of movement of the person detected from the first image is within an acceptable range, and if the direction and amount of movement are within an acceptable range, determines that the person detected from the first image and the person detected from the second image are the same person; Mechanical parking lot.

2. A mechanical parking lot capable of storing a vehicle that has entered a boarding / disembarking area in a parking space, an imaging device that images the interior of the boarding / deboarding compartment; a tracking unit that identifies the same person for each person detected in a plurality of images captured by the imaging device and generates tracking information that associates position information in each image of the person identified as the same person with each other; a determination unit that determines whether or not a closing operation of closing an entrance / exit door of the boarding / de-boarding compartment that has been opened for the purpose of entering or leaving the compartment can be started based on the tracking information, the determination unit determining that the closing operation cannot be started when the tracking information indicates that the person is present in the boarding / de-boarding compartment; Equipped with the tracking unit identifies the person detected from the first image and the person detected from the second image as the same person when an acute angle formed between a direction of movement of the person detected from a first image captured by the imaging device and a direction of movement of the person detected from a second image captured by the imaging device and temporally later than the first image is equal to or less than a predetermined threshold angle; Mechanical parking lot.

3. The system includes a detection unit that detects people from images captured by the imaging device using a trained model generated by machine learning using training data including training images that include people, the trained model outputting person detection information including position information of the people when an image is input. A mechanical parking lot according to claim 1 or 2.

4. A mechanical parking lot as described in any one of claims 1 to 3, wherein the judgment unit determines that the closing operation cannot be started if the tracking information indicates that the person has not left the boarding / exiting area at the time of entry.

5. A mechanical parking lot as described in any one of claims 1 to 4, wherein the judgment unit determines that the closing operation cannot be started if, at the time of leaving, the tracking information indicates that the person has not gotten into the vehicle to be left inside the boarding and disembarking compartment and has not left the boarding and disembarking compartment.

6. the imaging device includes a first imaging device and a second imaging device having an imaging area that is at least partially different from that of the first imaging device; the first image is an image captured by the first imaging device, and the second image is an image captured by the second imaging device; A mechanical parking lot according to any one of claims 1 to 5.

7. A mechanical parking lot as described in any one of claims 1 to 6, wherein the judgment unit determines that the closing operation cannot be started if the number of people detected inside the boarding / deboarding compartment at the time of entry does not match the number of people leaving the boarding / deboarding compartment indicated by the tracking information.

8. A mechanical parking lot as described in any one of claims 1 to 6, wherein the judgment unit determines that the closing operation cannot be started if, at the time of leaving, the number of people who have entered the boarding and disembarking space indicated by the tracking information does not match the number of people who have boarded the vehicle to be left in the boarding and disembarking space indicated by the tracking information plus the number of people who have left the boarding and disembarking space indicated by the tracking information.

9. an ID assigning unit that assigns an ID to a person detected from an image captured by the imaging device; A mechanical parking lot as described in any one of claims 1 to 8, wherein the judgment unit judges that the closing operation cannot be started if, at the time of entry, the tracking information indicates that there is someone among the people assigned IDs who has not left the lot.

10. an ID assigning unit that assigns an ID to a person detected from an image captured by the imaging device; A mechanical parking lot as described in any one of claims 1 to 8, wherein the judgment unit judges that the closing operation cannot be started if, at the time of leaving the parking lot, the tracking information indicates that among the people assigned IDs, there is one who has not entered the vehicle and has not left the parking lot.

Images