WO2019119063A1

WO2019119063A1 - Car park way finding system

Info

Publication number: WO2019119063A1
Application number: PCT/AU2018/051391
Authority: WO
Inventors: Allan Jansen
Original assignee: Divvy Parking Pty Ltd
Priority date: 2017-12-22
Filing date: 2018-12-21
Publication date: 2019-06-27

Abstract

This disclosure relates to systems and methods for assisted way- finding of a vehicle in a parking lot. A camera captures an image of the vehicle and a data store stores an association between image features and allocated spaces in the parking lot. A display displays indicia of a path. A processor determines an image feature when the vehicle is in a field of view of the image capture device. The image feature is adapted to distinguish the image of the vehicle from an image of another vehicle. The processor also determines an indicium of a path to an allocated space based on the association between the image feature of the image and the allocated space in the parking lot stored in the data store and displays the indicium on the display for assisted wayfinding of the vehicle to the allocated space in the parking lot.

Description

"Car park way finding system"

Cross-Reference to Related Applications

[0001] The present application claims priority from Australian Provisional Patent

Application No 2017905168 filed on 22 December 2017, the contents of which are incorporated herein by reference in their entirety.

Technical Field

[0002] This disclosure relates to systems and methods for assisted way- finding of a vehicle in a parking lot.

Background

[0003] Modern parking lots, also known as car parks, tend to be large multi-level lots with many hundreds, if not thousands of parking spaces available. A vehicle entering these complexes will often find it difficult navigating the entirety of the lot to find an empty space.

[0004] Any discussion of documents, acts, materials, devices, articles or the like which has been included in the present specification is not to be taken as an admission that any or all of these matters form part of the prior art base or were common general knowledge in the field relevant to the present disclosure as it existed before the priority date of each of the appended claims.

[0005] Throughout this specification the word "comprise", or variations such as "comprises" or "comprising", will be understood to imply the inclusion of a stated element, integer or step, or group of elements, integers or steps, but not the exclusion of any other element, integer or step, or group of elements, integers or steps.

Summary

[0006] There is provided a computer node for assisted wayfinding of a vehicle in a parking lot comprising: an image capture device to capture an image of the vehicle; a data store to store an association between image features and allocated spaces in the parking lot; a display to display indicia of a path; a processor to: determine an image feature of an image of a vehicle captured by the image capture device when the vehicle is in a field of view of the image capture device, wherein the image feature is adapted to distinguish the image of the vehicle from an image of another vehicle; determine an indicium of a path to an allocated space based on the association between the image feature of the image and the allocated space in the parking lot stored in the data store; and display the indicium on the display for assisted wayfinding of the vehicle to the allocated space in the parking lot.

[0007] A node may be advantageously positioned in any location of a parking lot such that it may provide navigation assistance to a vehicle via the display. The display will show a indicium of a path to the allocated space for that vehicle which assists the vehicle in navigating the parking lot. This is particularly useful in a large parking lot where there may be multiple level changes and turns in order for the driver of the vehicle to find their allocated space. Further the node allows for a parking lot operator to operate their parking lot more effectively. As a result more spaces can be allocated prior to the car entering the parking lot and therefore the operator of a parking lot may be less reliant on unallocated drive-ins.

[0008] An additional advantage of this present disclosure is that it enables a parking solution whereby a user can drive up to a parking lot without an allocated space, and have a space dynamically allocated substantially instantaneously. The system as contemplated by the present disclosure can direct the vehicle to the newly allocated space which the vehicle should be able to easily follow. It also allows an operator flexibility in allocating spaces. For example, spaces closer to exits can be given a premium as there would be more demand and customers may be willing to pay for the convenience. Currently it is hard to do because most ticketing solutions are based on entry/exit time rather than the space used by the vehicle.

[0009] Preferably, the processor receives the association between the image feature of the image and the allocated space in the parking lot.

[0010] Preferably, the processor further distinguishes the image of the vehicle from an image of another vehicle.

[0011] Preferably, distinguishing the image of the vehicle from an image of another vehicle comprises identifying the vehicle based on the image of the vehicle. [0012] Preferably, identifying the vehicle comprises determining one or more attributes of the vehicle.

[0013] Preferably, the one or more attributes of the vehicle include: colour; shape; weight; make; model; licence plate; and any other identifying feature of the vehicle.

[0014] Preferably, the processor further detects the presence of the vehicle for the image capture device to capture the image of the vehicle.

[0015] Preferably, the processor detects the presence of the vehicle by utilising the sensor.

[0016] Preferably, the sensor comprises one or more of the following: a motion sensor; temperature sensor; sound sensor; weight sensor; and any sensor that can be used to determine the presence of the vehicle.

[0017] Preferably, determining an indicium of a path to an allocated space based on the association between the image feature of the image and the allocated space in the parking lot stored in the data store comprises: sending the image feature to a server via a communications network; receiving data representing an allocated space associated with the image feature from the server via the communications network; and storing the data representing an allocated space associated with the image feature in the data store.

[0018] Preferably, an indicium includes one or more of: an arrow; a direction; a map; a representation of part of the path; a level; a vertical height; a measure of distance; and an orientation.

[0019] Preferably, the processor further determines an indicium of a path from an allocated space to an exit of the parking lot.

[0020] There is provided a computer implemented method of assisted wayfinding of a vehicle in a parking lot comprising: determining an image feature of an image of a vehicle captured by an image capture device when the vehicle is in a field of view of the image capture device, wherein the image feature is adapted to distinguish the image of the vehicle from an image of another vehicle; determining an indicium of a path to an allocated space based on the association between the image feature of the image and the allocated space in the parking lot stored in the data store; and displaying the indicium on a display for assisted wayfinding of the vehicle to the allocated space in the parking lot.

[0021] There is provided software, being machine readable instructions, that when performed by a computer node causes the computer node to perform the above method.

[0022] There is provided a computer system for assisted wayfinding of a vehicle in a parking lot comprising: one or more of the nodes described above; an image capture device; a network communication path; a processor to: capture an image of the vehicle when the vehicle is in a field of view of the image capture device; identify the vehicle from the image; determine an allocated space in the parking lot associated with the vehicle based on the vehicle identified from the image; determine an image feature of the image, wherein the image feature is adapted to distinguish the image of the vehicle from an image of another vehicle; create an association of the image feature and the allocated space; send the association of the image feature and the allocated space over the network communication path to the one or more nodes.

[0023] Preferably the processor is further adapted to: determine an indicium of a path to the allocated space based on the association between the image feature of the image and the allocated space in the parking lot stored in the data store; and send the indicium over the communication path to the one or more nodes.

Brief Description of Drawings

[0024] Fig. 1 is an illustration of an example of a vehicle entering a parking lot and navigating to an allocated space.

[0025] Fig. 2 is an example illustration of a system.

[0026] Fig. 3 is an example node.

[0027] Fig. 4 is an illustration of a method for assisted wayfinding of a vehicle.

[0028] Fig. 5 shows four example images captured by image capture devices. [0029] Fig. 6 illustrates six example indicia to be displayed on a display.

Description of Embodiments

[0030] Overview

[0031] The following disclosure describes a computer node for assisted wayfinding of a vehicle 102 in a parking lot 100. The node 130, 132, 134,136 comprises an image capture device 140 to capture an image of the vehicle 160; a data store to store an association between image features and allocated spaces 170 in the parking lot; a display 142 to display indicia of a path; and a processor.

[0032] The processor determines an image feature of an image of a vehicle 160 captured by the image capture device 140 when the vehicle is in a field of view of the image capture device, wherein the image feature is adapted to distinguish the image of the vehicle from an image of another vehicle 104. The processor determines an indicium of a path (144, in this example the indicium is an arrow) to an allocated space 170 based on the association between the image feature of the image 160 and the allocated space 170 in the parking lot 100 stored in the data store. The processor then displays the indicium 144 on the display 142 for assisted wayfinding of the vehicle to the allocated space in the parking lot.

Basic vs Advanced nodes

[0033] The present disclosure contemplates at least two types of nodes: basic nodes and advanced nodes.

[0034] Basic nodes are nodes that have less hardware requirements than advanced nodes. That is, a basic node may have a low-resolution camera from which the colour of the vehicle or rough shape of the vehicle may be able to be determined. Further the basic node may have limited processing power. As such the node can be produced and sold cheaply, albeit with limited functionality. In the context of a system of nodes, this distinguishing of nodes means not all nodes need to have significant amount of processing power or high resolution cameras. Some of the nodes may be able to communicate sufficient information about a vehicle to other nodes such that a basic node with limited hardware and functionality can provide an indicium of a path to an allocated space in the parking lot. [0035] Alternatively, a node may be an advanced node in a further embodiment. It is intended that an advanced node has additional or better hardware than basic nodes. For example, an advanced node may have a camera with a higher resolution and optionally has higher processing power too. This may come with higher power requirements which means a larger battery or ensuring sufficient power supply. Functionally, an identification of a vehicle can be made from an image of the vehicle taken by the advanced node. It is notable that in a system with multiple basic nodes, it would be expected there would be at least one advanced node. The advanced node therefore would be able to determine the identity of a vehicle which may be difficult for a basic node. As described in the examples below, this would typically involve determining the image features of the image captured by the image capture device. The image features could be determined by utilising image analysis.

Parking lot

[0036] A parking lot as the term is used in the present disclosure is a place where vehicles can be parked or left stationary. This includes complex multi-level parking lots or parking lots on a single level. A parking lot may be indoors (such as an enclosed or underground lot), or outdoors (such as a lot surrounding a large shopping mall). A parking lot does not have to be a designated parking lot and may be just a temporary area for parking such as a field or enclosure for a large event, such as a sports match or music act. It is intended in this disclosure that a parking lot refers to any area whereby a person can be allocated a portion of the total available area in order to park a vehicle. This system can be set up to operate on temporary parking areas such as fields or parks.

Simple parking lot example

[0037] To return again to Fig. 1, this illustration is an example of a vehicle 102 entering a parking lot 100 and navigating to an allocated space 170. In the example of Fig. 1, a parking lot operator has installed a number of nodes (130, 132, 134, 136) that are in communication with each other via a network. In this example, each of these nodes displays to the vehicle a direction that the vehicle should take into order to get to the allocated space that includes going down a down ramp 112,114. [0038] Modern technology has enabled both instantaneous and advance reservation of parking spaces which may require a vehicle to navigate through much of the parking lot in order to find the allocated space, depending on how full the parking lot is. The directions to the allocated space may be known to the user if they are regular users of the parking lot, but it may be unfamiliar to the user if they have not used the parking lot before or if the allocated space is not been allocated to that user before.

[0039] As the vehicle 102 enters the parking lot 100, the first node 130, in this example an advanced node, captures an image of the vehicle from the image capture device 140. The advanced node determines an image feature of an image of a vehicle captured by the image capture device when the vehicle is in a field of view of the image capture device, wherein the image feature is adapted to distinguish the image of the vehicle from an image of another vehicle. In this case the node determines that the vehicle is a blue sedan with silver hub caps. In simplistic terms, the image features are mostly blue with some silver.

[0040] At this point the advanced node 130 is able to make an association between the image features and the allocated space 140, for example blue with silver is assigned the allocated space 170. In this example, the advanced node communicates this association between the image features and allocated space 170 in the parking lot 100 to the other nodes 132, 134, 136.

[0041] The other nodes being basic nodes do not have the hardware requirements of an advanced node. The basic nodes do not necessarily need to identify the vehicle directly and instead rely on the fact that the advanced node 130 has already identified the vehicle. The association of image features and an allocated space that was communicated to the basic nodes from the advanced node 130 means that the basic nodes can simply capture a basic image and perform limited image feature analysis in order to display an indicium of a path to the allocated space. In this example, the basic nodes only need to distinguish colour (blue with silver) and make (sedan). This may be sufficient information to direct the blue sedan to its allocated space 140.

[0042] Once a node has determined an indicium of a path to an allocated space based on the association between the image feature of the image and the allocated space in the parking lot stored in the data store it can then display the indicium on the display for assisted wayfinding of the vehicle to the allocated space in the parking lot. In this example, the indicia are arrows directing the vehicle at each of the intersections toward the allocated space 140.

Example system

[0043] Fig. 2 illustrates an example system 200, where the nodes 130, 132, 134 are in communication with each other via a network communication path to a network 210. The network 210 may be wired (such as Ethernet) or wireless (Wi-Fi) or a combination of both, depending on the network interface device in the individual nodes 130, 132,134,136. There is a trade-off of performance characteristics between wired and wireless. For example, wired networks may be faster with higher capacity but the nodes may be fixed in place. Wireless networks may mean nodes can be moved more easily, but with less speed or capacity.

Wireless networks may also be susceptible to interference and therefore may not be suitable for large multilevel parking lots, but may be sufficient for single level outdoor parking lots. The implemented network depends therefore on which of the performance characteristics are desired.

[0044] In the example of Fig. 1 , one of the nodes 130 (an advanced node) makes a request to the server 220 to determine the allocated space for the identified vehicle. In order for the space to be allocated in the first place, a user 206 on a mobile device 208 or a user 250 on a web terminal 252 may connect to the internet 212 to make a reservation of a space in a parking lot for the vehicle 102. The reservation of a space in the parking lot is handled by a server 220, which in this case is connected to the same network as the node network 210.

[0045] The server 220 is in communication with a data store 230. The data store has a user information store 232 that stores relevant user information, such as a user name and associated vehicle details, in particular, licence plate numbers. The data store 230 also has a data store of allocated spaces 234, which are the spaces that have been allocated out of all the available spaces in a parking lot. In some embodiments, each of the spaces in a parking lot will be stored in the data store 234, but where the allocated ones will be flagged in the record in the database and associated with user information or vehicle information to which the space has been allocated for the specified amount of time. [0046] A user 250 of the vehicle 102 may have reserved online through a web-based interface on a web terminal 252. The web-based interface would typically be accessed through an internet browser, such as Chrome, Safari, Internet Explorer or Firefox.

Alternatively, the user 206 of the vehicle 102 could have used a mobile application on a mobile device 208 to perform the same reservation.

[0047] The server 220 may provide to the user 206, 250 a list of available spaces in a specified parking lot at a given time or range of times. The user 206,250 may then select a space in the parking lot, a length of time and a vehicle 102 (if the user has more than one vehicle the user may be required to select the vehicle, alternatively defaults may be used).

The server 220 will then store in the allocated spaces data store 234 an association between a vehicle and an allocated space.

[0048] Although not illustrated, a further alternative is that the user has paid for or otherwise has a reserved space where, for example, a business in a building near the parking lot has a number of spaces allocated to them by the manager of the parking lot. In each of these cases, the allocated space 140 associated with the vehicle 102 is known to the system beforehand.

[0049] The allocated spaces data store 234 may contain spaces for more than just one parking lot. Historical data may also be relevant for the user to see which spaces they have been allocated in the past. For example, the user may want to reserve a space which they have frequently used because it is a convenient space.

[0050] In some embodiments, the data store 230 may also store image features 236 and vehicle attributes 238 which can be associated with allocated space when a reservation is made by a user. In this case, the server 220 may send the association of the image feature and the allocated space over the network communication path to the one or more nodes.

[0051] Vehicle attributes may be provided to a node for more easily identifying image features that distinguish images of the vehicle from another vehicle. If the node is not provided with vehicle attributes, the node may determine one or more attributes of the vehicle itself. Vehicle attributes include: colour; shape; weight; make; model; licence plate; and any other identifying feature of the vehicle. [0052] Providing vehicle attributes to nodes via the network additionally may be useful where a vehicle enters multiple parking lots and so the same determinations of attributes may not need to be done as often. It may also be possible for a parking lot to be serviced entirely by basic nodes if it is statistically likely that vehicles can be identified from a combination of vehicle attributes without having to rely on licence plates.

[0053] The system may give the image a score according with how well the image matches a vehicle based on the attributes of the vehicle. For example, an image that has blue and silver within an estimated geometry of a sedan in the image may be a 80% match to the vehicle 102 which is blue with silver. An image with less silver may only be a 60% match, and an image with no silver may be 40% and so on. Nodes may keep a list of vehicles that are currently present in a parking lot and may perform a score analysis based on the list of vehicles in order to determine the most likely vehicle match from the image features, that is, the vehicle with the highest score.

Example node

[0054] Fig. 3 illustrates an example node 130. The example node 130 has a processor 302, a display interface device 310, a network interface device 312, an image capture device 314, a memory 320 and a bus by which the node components can communicate 304. The memory 320 has an image module 322, a network module 324 and a database module 326 and a display module 327 (the node may optionally have a sensor module 328). This example node has a display 330 and an image capture device 340 which communicate with the other node components via the corresponding interface device (310, 314). The network interface device allows the node components to communicate with the network 210.

[0055] In this example, the image capture device 340 captures an image of the vehicle when a vehicle (such as 102 in Fig. 1) is in a field of view of the image capture device. This image in this example is a high resolution image stored in a JPEG format, but there may be many other formats of images such as RAW, PNG, BMP, TIFF and GIF. There are also many other types of image capture devices such as a webcam or a simple camera, which may capture images in one or more of the above mentioned formats. In some embodiments the processor 302 may utilise instructions in an optional sensor module 328 to interface with a sensor (not illustrated) to detect the presence of the vehicle for the image capture device to capture the image of the vehicle. A sensor may be one or more of the following: a motion sensor;

temperature sensor; sound sensor; weight sensor; and any sensor that can be used to determine the presence of the vehicle. A motion sensor may detect any form of movement, and more specifically any movement that is like , a temperature

[0056] The image of the vehicle is communicated via the image capture interface device 340 and stored in the image module memory 322. The processor 302 then using instructions stored in the image module 322 performs an image analysis of the image stored in the image module 322 to determine one or more image features of the image.

[0057] The image analysis of the image stored in the image module 322 is to determine one or more image features of the image that are adapted to distinguish an image of the vehicle from an image of another vehicle. It is to be noted that the node 130 does not necessarily need to distinguish the image of the vehicle from all other vehicles, which may be many millions of vehicles and therefore computationally infeasible. The node 130 may simply distinguish the vehicle 102 from other vehicles that may be in the parking lot. It is to be noted that it is intended to be a statistical likelihood that a vehicle can be distinguished from another vehicle. That is, an image feature distinguishes an image of a vehicle from an image of another vehicle with a degree of probability. There may be extreme examples where distinguishing cannot be easily done, for example where two cars of the same make, model and colour enter the parking lot. In this case, the node may have to rely entirely on the licence plate details (which can be assumed to be unique) in order to determine the one or more image features that distinguish the vehicle from another vehicle. Symbol recognition does not necessarily have to be performed in order to identify a vehicle from the licence plate details. For example, there may be pixel counts or even a count of vertical edges which distinguishes the letter T (at least 1 vertical edge) from an S (no vertical edges).

[0058] The node may in addition make heuristic assumptions for computational efficiency, such as noting that most vehicles are parked within 10 minutes of entering the parking lot and therefore do not need way-finding assistance. As a result, the node only needs to consider other vehicles that have entered the parking lot within the previous 10 minutes. There may be circumstances for a basic node to misdirect a vehicle, but given that an image feature is intended to distinguish a vehicle from another vehicle, an occurrence of this should be rare.

In such cases, an advanced node may recognise statistically problematic situations and, if possible, provide additional assistance to the other nodes. For example, if there were another blue car within a short period of time, the advanced node may provide additional image features in order to assist the basic nodes. In such a case, the degree to which other image features can be provided depends on the hardware of the basic nodes which is dependent on how the system is rolled out. In some problematic situations, the node can simply display nothing, an error output, or an identification number for the allocated space whereby the vehicle may simply have to navigate to the allocated space 170 without assistance.

[0059] The processor 302 may determine the one or more image features of the image based on the hardware or software capabilities of the other nodes (132, 134, 136 in Fig. 1 and Fig.

2). The one or more image features are then shared with the other nodes 132,134,136 as well as the association between the one or more image features and an allocated space. For example, the node 130 may determine a colour of the vehicle in the image given that the image capture devices of nodes 132,134,136 are highly capable of distinguishing colour of an image, but less capable of distinguishing shapes.

[0060] The processor 302 may execute instructions to identify the vehicle that is captured in the image. One way in which the vehicle may be identified is by determining the attributes of the vehicle based on the image of the vehicle. Similarly, to the above the processor 302 may perform the image analysis in the image module 322 In the case of advanced nodes, the node is typically able to determine the vehicle’s licence plate by performing an Optical Character Recognition of the image of the vehicle. The advanced node may determine further image features of the image of the vehicle such as the colour and make.

[0061] The processor 302 may then execute instructions in the database module 326 to determine an allocated space for the vehicle. The processor 302 may send the image feature to the server 220 via a communications network 210. The processor may then receive data representing an allocated space associated with the image feature from the server via the communications network. The processor 302 may then store the data representing an allocated space associated with the image feature in the database module data store 326.

[0062] If the instructions in the database module 326 determine that there is no space allocated, the node may execute additional instructions to perform a substantially

instantaneous allocation which may involve a further communication with the server 220. Alternatively, the processor 302 may execute instructions relating to default allocations such as where unallocated vehicles are directed to a designated unallocated parking area.

[0063] Then the processor 302 executes instructions in the display module 327 to determine an indicium of a path to the allocated space based on the association between the image feature of the image and the allocated space in the parking lot stored in the data store 320. Typically a path-finding algorithm would be used such as A* search algorithm or Djikstra’s algorithm. However, there may be bespoke path- finding algorithms that suit pathfinding in a specific parking lot.

[0064] The processor 302 executes instructions in the display module to display the indicium of a path to the allocated space on a display 330. There are many different types of displays that are contemplated by the present disclosure including high resolution screens, indicator lights, and one or more Light Emitting Diodes (LEDs) such as in an 8x8 matrix as indicated in the example display 330. The example display 330 is a collection of LEDs which are coordinated by the processor 302 such that they display an indicium of an arrow. The display is displaying an arrow on the display for assisted wayfinding of the vehicle to the allocated space in the parking lot. A display may be integrated into the floor, walls or ceiling of a parking lot or may be a mobile or fixed standalone display.

Example method

[0065] Fig. 4 illustrates an example method 400 for assisted way finding of a vehicle to an allocated space. The first step 410 is determining an image feature of an image of a vehicle captured by an image capture device when the vehicle is in a field of view of the image capture device, wherein the image feature is adapted to distinguish the image of the vehicle from an image of another vehicle.

[0066] The second step 420 is determining an indicium of a path to an allocated space based on the association between the image feature of the image and the allocated space in the parking lot stored in the data store.

[0067] The third step 430 is displaying the indicium on a display for assisted wayfinding of the vehicle to the allocated space in the parking lot. Features

[0068] An aspect of this present disclosure that is common to both basic and advanced nodes is determining image features. Fig. 5 includes four example images captured by different nodes of a vehicle navigating an outdoor parking lot. The image 502 is an image captured by an advanced node whereas images 504, 506 and 508 are captured by basic nodes in the same position where the image capture device that captured each of the images is of decreasingly lower quality. The basic node images 504, 506 and 508 are lower resolution than the advanced node image 502. 508 is monochrome.

[0069] It is to be understood that more image features can be determined from an image of a more powerful image capture device. For example, as can be seen the image quality of the advanced node’ s image is substantially higher resolution with more colour. The image from an advanced node can therefore be used to identify the vehicle based on the number of image features that can be determined from the image. In particular, an advanced node may be able to determine the vehicle’s licence plate. Depending on the image analysis to be performed, the attributes of the vehicle include: colour; shape; weight; make; model; licence plate; and any other identifying feature of the vehicle.

[0070] In contrast to the high resolution image of 502, notably the colour reproduction of 504 and 506 is significantly diminished from 502. The vehicle 502 is silver, but the colour in 504 has purple tones. There is similar colour tone in 506 but much of the colour information has been lost. Nevertheless shapes could still be identified. It is apparent therefore that the image features to be used to distinguish a vehicle are dependent on the imaging capabilities of the basic nodes.

[0071] It may still be possible to perform an image feature analysis in order to determine the vehicle with only limited image features. In some systems a camera that only captures black and white may still be useful, as it still possible to determine attributes of a vehicle such as shape or size. In some cases, the image can be manipulated in order to determine image features. For example, the image capture device may capture an image of an empty parking lot. Then, when the image capture device is capturing an image of a vehicle, image analysis techniques can be used to remove the elements from the image that are identified as part of the parking lot such as pillars, walls and roads. This is in essence a subtraction of images with the parking lot image being subtracted from an image of the vehicle. In some cases this makes it easier to determine the vehicle because image data that is known to not contribute to determining a vehicle can be eliminated from further image analysis.

Licence plate recognition

[0072] There are many algorithms in the art that can be used for licence plate recognition and as such it would be understood by a person skilled in the art may apply one or more licence plate recognition algorithms if they were to implement the system of the present disclosure.

[0073] There are some general aspects in licence plate recognition that may be relevant. For example, there may be in addition some form of localisation, where localising is an algorithmic function that determines what aspect of the image captured by the image capture device is the license plate. For example, the algorithm must rule out a vehicle's mirror, headlights, bumper and other features. In general, algorithms look for geometric shapes of rectangular proportion. Flowever, since a vehicle can have many rectangular objects on it, further algorithms may be needed to validate that the identified object is indeed a license plate.

[0074] The licence plate localisation algorithm may look for characteristics that would indicate that the object is a license plate. For example, a small number of combinations of colour for a licence plate cover a majority of vehicles registered in New South Wales. In particular, black on yellow and white on black are common. The algorithm may specifically be tailored in order to accurately work for those instances. The algorithm may search for a similar background colour of unified proportion and contrast as a means to differentiate objects on a vehicle. Once licence plate localisation occurs, other complementary algorithms such as normalisation and optical character recognition can be applied.

Additional example indicia and displays

[0075] Fig. 6 illustrates six example indicia to be displayed on a display of a node. An indicium includes one or more of: an arrow; a direction; a map; a representation of part of the path; a level; a vertical height; a measure of distance; and an orientation. [0076] The type of indicia that can be displayed depends on the type of display although each type of display may support different indicia. For example, 602, 604 and 606 are all LED displays where by the black circle indicates that a LED is on and white indicates that an LED is off. The indicia 602 is an arrow which can be used to direct a vehicle in a specific direction. 604 is a basic illustration of a map which can be used to direct a vehicle into a specific parking space. Such an indicia may be more useful closer to an allocated space. The indicia on 606 is a path, which the driver of a vehicle may note in order to navigate to either the next node or the allocated space.

[0077] The displays 610, 612 and 614 are higher resolution displays. 610 is a black and white map but also indicating directions for a vehicle to take in order to navigate through to the parking lot. The display in 612 is a high resolution image of the allocated space, where the indicia includes a level (level 2) and a measure of distance (5.3 metres away) which assists the driver of the vehicle in navigating to the allocated space. The high resolution image in 614 is identical but displays an arrow overlayed over the image to indicating a clear direction and the allocated space itself, which may not be as clear in the indicia of 612.

Time based Allocations

[0078] It is to be noted that in the above examples the allocations are time-based, meaning that the same space in a parking lot can be allocated to different vehicles if the time does not overlap. In order to allocate via time, the system may operate on a sufficiently small intervals such as 15 minutes or 30 minutes. In this case, the allocation of time may be a multiple of the selected interval. There may also be a factor of additional time to resolve clashing allocations. For example, if the allocations of spaces are by 15 minute intervals, it is possible that a vehicle may not have exited the allocated space by 15 minutes after the end of the allocation. However, it may be determined it is highly likely the vehicle may have exited after 30 minutes, and very likely that the vehicle has exited after an hour. In this case, there may be leeway given of 1 hour between allocations.

[0079] There may also be additional mechanisms in place within the system to ensure that a space that is intended to be available actually is available, such as where a space has been taken by a vehicle that has overstayed its allocated time. Many parking lots currently have parking sensors for example, that can indicate via a green or red light as to whether a space is currently occupied. These parking sensors can therefore similarly be used to indicate available spaces for allocation.

Dynamically allocating spaces

[0080] Most parking lots have a mechanism such as 106 in Fig. 1 that allows for the vehicle to enter on a timed and therefore chargeable basis. For example, parking lots generally have a boom gate 106 at each of their entrances. Currently when a vehicle 102 arrives at the entrance 104 where the parking lot 160 has a ticketing machine that produces a ticket, which is timestamped. The charge for use of the parking lot 160 is based on the time that the car is present in the parking lot and this is calculable from the time that is timestamped on the ticket. In some cases, the parking lot may charge a flat rate for a certain amount of time, or charge more or less for different times of the day, week, month or year. An embodiment of the present disclosure extends how parking lots 160 could operate. For example, that a space in the parking lot 160 may be allocated at the point at which the vehicle enters the parking lot at the boom gate 106. This is a dynamic allocation of spaces in a parking lot.

[0081] It will be appreciated by persons skilled in the art that numerous variations and/or modifications may be made to the above -described embodiments, without departing from the broad general scope of the present disclosure. The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive.

Claims

CLAIMS:

1 A computer node for assisted wayfinding of a vehicle in a parking lot comprising: an image capture device to capture an image of the vehicle;

a data store to store an association between image features and allocated spaces in the parking lot;

a display to display indicia of a path;

a processor to :

determine an image feature of an image of a vehicle captured by the image capture device when the vehicle is in a field of vie of the image capture device, wherein the image feature is adapted to distinguish the image of the vehicle from an image of another vehicle;

determine an indicium of a path to an allocated space based on the association between the image feature of the image and the allocated space in the parking lot stored in the data store; and

display the indicium on the display for assisted wayfinding of the vehicle to the allocated space in the parking lot.

2 A computer node according to claim 1 , wherein the processor receives the association between the image feature of the image and the allocated space in the parking lot.

3 A computer node according to claim 1 or 2 wherein the processor further distinguishes the image of the vehicle from an image of another vehicle.

4 A computer node according to claim 3 wherein distinguishing the image of the vehicle from an image of another vehicle comprises identifying the vehicle based on the image of the vehicle.

5 A computer node according to claim 4 wherein identifying the vehicle comprises determining one or more attributes of the vehicle.

6 A computer node according to claim 5 wherein the one or more attributes of the vehicle include:

colour; shape;

weight;

make;

model;

licence plate; and

any other identifying feature of the vehicle.

7 A computer node according to any of the preceding claims wherein the processor further detects the presence of the vehicle for the image capture device to capture the image of the vehicle

8 A computer node according to claim 7, further comprising a sensor, wherein the processor detects the presence of the vehicle by utilising the sensor.

9 A computer node according to claim 8 wherein the sensor comprises one or more of the following:

a motion sensor;

temperature sensor;

sound sensor;

weight sensor; and

any sensor that can be used to determine the presence of the vehicle.

10. A computer node according to any of the preceding claims wherein determining an indicium of a path to an allocated space based on the association between the image feature of the image and the allocated space in the parking lot stored in the data store comprises:

sending the image feature to a server via a communications network;

receiving data representing an allocated space associated with the image feature from the server via the communications network; and

storing the data representing an allocated space associated with the image feature in the data store.

11. A computer node according to of any of the preceding claims wherein an an indicium includes one or more of:

an arrow; a direction;

a map;

a representation of part of the path;

a level;

a vertical height;

a measure of distance; and

an orientation.

12. A computer node according to any of the preceding claims wherein the processor further determines an indicium of a path from an allocated space to an exit of the parking lot.

13. A computer implemented method of assisted wayfinding of a vehicle in a parking lot comprising:

determining an image feature of an image of a vehicle captured by an image capture device when the vehicle is in a field of view of the image capture device, wherein the image feature is adapted to distinguish the image of the vehicle from an image of another vehicle;

determining an indicium of a path to an allocated space based on the association between the image feature of the image and the allocated space in the parking lot stored in the data store; and

displaying the indicium on a display for assisted wayfmding of the vehicle to the allocated space in the parking lot.

14. Software, being machine readable instructions, that when performed by a computer node causes the computer node to perform the method of claim 13

1 5. A computer system for assisted wayfinding of a vehicle in a parking lot comprising:

one or more nodes according to any of the claims 1 to 12;

an image capture device;

a network communication path;

a processor to:

capture an image of the vehicle when the vehicle is in a field of view of the image capture device;

identify the vehicle from the image; determine an allocated space in the parking lot associated with the vehicle based on the vehicle identified from the image; determine an image feature of the image, wherein the image feature is adapted to distinguish the image of the vehicle from an image of another vehicle;

create an association of the image feature and the allocated space;

send the association of the image feature and the allocated space over the network communication path to the one or more nodes.

16. A computer system according to claim 15 where the processor is further adapted to:

determine an indicium of a path to the allocated space based on the association between the image feature of the image and the allocated space in the parking lot stored in the data store; and

send the indicium over the communication path to the one or more nodes.