Detailed Description
Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and should be considered as merely exemplary. Accordingly, one of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
An embodiment of a first aspect of the present disclosure provides a parking prompting method, as shown in fig. 1, including:
Step S101: under the condition that the target vehicle enters the set area is determined, tracking the position of the target vehicle according to the first image and the second image of the target vehicle to obtain a tracking result; the first image and the second image are obtained by shooting different ranges around the target vehicle, and the pixel positions corresponding to at least one same position point in the first image and the second image have a calibrated association relationship;
Step S102: according to the tracking result, under the condition that the target vehicle stops in the set area, the stop information of the target vehicle is obtained;
Step S103: and sending parking prompt information to a terminal corresponding to the target vehicle according to the parking information and the parking space information in the set area.
The set area may be an area defined by an empty space in a closed place such as an empty space beside a road, a non-road area beside a building, or a district. The method can be generated by directly marking and calibrating an actual area, or can be generated by calibrating an image shot by a camera and corresponding a calibrated area in the image to an actual scene.
In one implementation, the determination that the target vehicle enters the set area may be that the target vehicle is detected to enter the set area in a captured image or video by a preset imaging device.
In another implementation, the determination that the target vehicle enters the set area may be that an entrance through which the vehicle enters the set area is determined in advance at the set area, a sensor is provided at the entrance, and the travel direction of the target vehicle is detected by the sensor as a direction from outside the set area to enter the set area, thereby determining that the target vehicle enters the set area.
The first image and the second image of the target vehicle may be images obtained by capturing the target vehicle with two cameras having different parameters, or images obtained by capturing the target vehicle with the same camera adjusted to different parameters such as focal lengths.
Further, the first image may include a plurality of images, and the second image may include a plurality of images. The photographing ranges between the plurality of first images may be the same or different, and the photographing ranges between the plurality of second images may be the same or different.
Further, the first image and the second image are obtained by photographing different ranges around the target vehicle, which may mean that the photographing ranges of the first image and the second image are different in size when the photographing device photographs the target vehicle. It may also mean that there is a non-overlapping region in the photographing ranges when the photographing device of the first image and the second image photographs the target vehicle. It may also mean that the photographing ranges of the first image and the second image when the photographing device photographs the target vehicle are different in size and there is a non-overlapping region in the photographing ranges.
In one embodiment, the position tracking of the target vehicle is performed according to the first image and the second image of the target vehicle, and the position tracking of the target vehicle may be performed according to different ranges in the first image and the second image. For example, a first image covers a A, B, C partition in a set area, a second image covers a C, D, E partition in the set area, a calibrated association relation exists between a C partition in the first image and a C partition in the second image, a target vehicle runs through an A partition and a B partition from an entrance, when the C partition is formed, target vehicle information in the first image and the second image is associated, it is determined that the target vehicle starts to appear in the C partition of the second image, if the target vehicle reaches a D partition or an E partition from the C partition and stops in the D partition or the E partition, the stop partition of the target vehicle can be determined through tracking.
The pixel positions corresponding to at least one same position point in the first image and the second image can be the pixel positions corresponding to the same region, object or point in the first image and the second image respectively.
The pixel position may be the coordinates of one pixel point, or may be an area formed by a series of coordinates in two images.
The step of determining that the target vehicle stops in the set area according to the tracking result may be that the target vehicle stops running in the set area according to the tracking result and the running stopping time exceeds a set threshold.
Obtaining the stop information of the target vehicle may include obtaining at least one of stop position-related information, stop time-related information, stop state-related information, and the like of the target vehicle. The information related to the parking status may include whether to park in an illegal manner, such as occupying two parking spaces, which may cause a situation that other vehicles are difficult to park normally.
According to the parking information and the parking space information in the setting area, the parking prompt information is sent to the terminal corresponding to the target vehicle, and the prompt information can be sent to the terminal of the target vehicle according to whether the parking information belongs to a certain parking space in the setting area or whether the terminal is parked at the position of the parking space allowed to park in the setting area.
The terminal corresponding to the target vehicle may be a vehicle-mounted terminal corresponding to the target vehicle or a mobile terminal corresponding to the target vehicle, or may be a network information receiving account (such as a mailbox) corresponding to the target vehicle.
The parking guidance information may be guidance information related to parking management in a set area. For example, the charging prompt information, the charging-free prompt information, the prohibited parking information, and the parking charging information are information related to the parking management behavior in the set area.
The embodiment of the disclosure can be applied to a common parking lot, a semi-closed parking lot and a parkable space without any parking lot hardware facilities. The semi-closed parking lot can be that a plurality of entrances and exits exist in the parking lot, and vehicles cannot enter and exit from other positions except the entrances and exits, namely, the places except the entrances and exits of the parking lot are closed, and the entrances and exits of the semi-closed parking lot are not closed like the places of the traditional closed parking lot, such as barrier gates, sentry boxes and the like, so that the vehicles are forced to park.
It can be seen that, according to the embodiment of the disclosure, through images of different ranges captured by a target vehicle, the driving of the target vehicle after entering a set area can be tracked, the parking event of the target vehicle is detected, and according to the parking space information in the set area and the parking information when the target vehicle is parked, the parking prompt information related to parking is determined, so that the parking behavior of the vehicle in the set area is effectively managed.
In one embodiment, the parking information includes a target zone where a parking position is located, and obtaining the parking information of the target vehicle includes:
generating a corresponding virtual model in the first image or the second image according to the target vehicle;
and determining a target zone where the parking position of the target vehicle in the set area is located according to the virtual model.
The target partition is one of the plurality of partitions. The plurality of zones in the set area may be zones obtained by delineating or dividing a region requiring a parking management operation, such as a parkable region and a parkable-prohibited region, in the set area.
For example, as shown in fig. 2, a road area 202, a green belt area 203, a small building area 204, and an open ground 205 other than a road are present in the set area 201. The non-road open ground 205 is other areas than the road area 202, the green belt area 203, and the small building area 204 in the set area. The non-road open ground 205 may be delineated or divided to generate a plurality of partitions.
When dividing the open ground of the non-road, each independently existing open ground area can be directly used as a complete partition; it is also possible to divide the open ground 300 with a larger area into a plurality of sub-areas, each sub-area being divided into a sub-area, as illustrated in fig. 3 as sub-area 301, sub-area 302 and sub-area 303.
In this embodiment, the virtual model may be an icon simulating the target vehicle, for example, a rectangular icon is generated in the first image and the second image respectively, and corresponds to the target vehicle. The virtual model may be a model for simulating the target vehicle into a regular shape, such as a virtual geometric model.
The virtual model is further used for determining the coverage of the target vehicle in the set area by using a regular shape obtained by simulating the target vehicle.
According to the virtual model, determining a target zone where the parking position of the target vehicle in the set area is located, further comprising: and determining the coverage of the target vehicle in the set area or a projection graph obtained by projecting the target vehicle in the set area according to the virtual model, and determining a target partition where the parking position of the target vehicle in the set area is located according to the coverage or the projection graph.
It can be seen that in this embodiment, the set area is divided into a plurality of target areas, and the target area where the parking position of the target vehicle in the set area is located is determined according to the virtual model generated by the target vehicle in the first image or the second image, so that the accurate position of the target vehicle can be determined. When the line pressing and parking positions of the target vehicle possibly cover more than two subareas, the method can make clear and reasonable judgment on the target subarea where the target vehicle is located.
In one embodiment, the virtual model is a three-dimensional virtual model; according to the virtual model, determining a target zone where a parking position of a target vehicle in a set area is located, including:
determining a projection graph of the target vehicle in a set area according to the three-dimensional virtual model;
and determining the target partition according to the overlapping proportion of the projection graph and each partition in the plurality of partitions contained in the set area.
The three-dimensional virtual model may be a solid geometric model, such as a cube model. Or may be a stereoscopic icon such as a cube with a projected graphic. In a specific embodiment, a deep learning mode is adopted to learn key points, a 3D (three-dimensional) frame modeling is performed on a target vehicle, the 3D position of the vehicle is known, the vehicle is projected to a 2D (two-dimensional) picture, and the overlapping proportion of the vehicle and each partition is judged.
According to the three-dimensional virtual model, determining the projection graph of the target vehicle in the set area can be to project the three-dimensional virtual model to the set area to obtain the projection graph. The projection pattern of the target vehicle in the set area may be determined based on the three-dimensional virtual model, or the projection pattern of the target vehicle in the set area may be obtained from the three-dimensional virtual model generated based on the target vehicle.
In this embodiment, the overlapping ratio of the projection pattern and each of the plurality of partitions may be the overlapping ratio of the projection pattern and each of the plurality of partitions within the target vehicle surrounding setting range, and the overlapping ratio of the projection pattern and at least one partition outside the target vehicle setting range may default to 0.
In one embodiment, the target partition is determined according to the overlapping ratio of the projected pattern and each of the plurality of partitions, and the partition having the largest overlapping ratio may be defined as the target partition.
In this embodiment, according to the projection pattern of the three-dimensional virtual model of the target vehicle in the set area, the overlapping proportion of the projection pattern and each partition is determined, and the target partition is further determined according to the overlapping proportion, so that the target partition can be accurately determined according to the actual parking position of the target vehicle, and the situation that the specific partition to which the target vehicle belongs cannot be clarified when the target vehicle is parked near the edge positions of the plurality of partitions is avoided.
In one embodiment, according to parking information and parking space information in a set area, a method for sending parking prompt information to a terminal corresponding to a target vehicle includes:
And under the condition that the target subarea does not set up the parking space according to the parking information and the parking space information in the setting area, sending and recording parking prompt information about forbidden parking to a terminal corresponding to the target vehicle.
And judging that the target partition does not set a parking space, wherein the target partition does not correspond to any preset parking space information or is preset with a forbidden mark. The forbidden mark can be set through the first image and the second image, or a forbidden mark plate and other forbidden objects can be placed in the partition of the non-set parking space.
Furthermore, the target partition does not set up a parking space, and the target partition does not set up a dockable parking space in any time period within 24 hours of the whole day, namely, the parking space does not belong to a time-limited parking forbidden area, but is an absolute parking forbidden area.
The sending and recording of the parking prompt information about forbidden parking to the terminal corresponding to the target vehicle may be sending the parking prompt information about forbidden parking to the terminal corresponding to the target vehicle, and generating a record of the parking prompt information about forbidden parking.
The sending of the parking prompt information about stopping to the terminal corresponding to the target vehicle may be sending information including stopping prompt information, for example, "please stop here". The record of the parking prompt information about the prohibition of parking may be generated by recording the state in which the target vehicle is in the prohibition region.
In another implementation, a limited parking space can be set in the set area, in which case, the parking information can include a parking time, and if the target area is exactly in a period of time for allowing parking at the parking time included in the parking information, the target area can be determined to set the parking space; and when the time period for allowing parking passes, determining that the target partition does not set a parking place, and when the time period for allowing parking is ended, executing the steps of sending and recording parking prompt information about forbidden parking to the corresponding terminal of the target vehicle.
In this embodiment, a state that the target vehicle is in the forbidden region can be detected, and the state is recorded and prompted, so that the parked vehicle in the forbidden region is avoided. Under the condition that the forbidden area belongs to a fire-fighting channel and a passing-in and-out channel, the occupation of the channel resources by vehicles can be effectively avoided, and the effectiveness of the management of the set area is improved.
In one embodiment, the parking prompt method further includes:
under the condition that the target vehicle leaves the target zone, acquiring the parking time of the target vehicle in the target zone;
in the case where the parking time is smaller than the set parking time threshold, the record about the parking is released.
The method may further include the steps of obtaining a parking time of the vehicle in the target zone when the target vehicle leaves the target zone, obtaining a time when the target vehicle leaves the target zone when the target vehicle is detected to leave the target zone, determining a time when the target vehicle starts to park in the target zone according to a record of parking prompt information about forbidden parking, and determining a parking time of the target vehicle in the target zone according to the time when the target vehicle leaves the target zone and the time when the target vehicle starts to park in the target zone.
In one possible implementation, a record may be kept regarding the stop if the stop time is greater than a set stop time threshold.
In one possible implementation manner, in the case that the target vehicle leaves the target zone, the parking time of the vehicle in the target zone is acquired, or in the case that the target vehicle is detected to leave the target zone, the time when the target vehicle leaves the target zone is acquired, if the target zone is changed from a state in which a parking space is not established to a state in which a parking space is established at the time when the target vehicle leaves the target zone, the parking time of the target vehicle in the target zone is determined according to the stop time when the parking space is limited and the time when the target vehicle starts to park in the target zone.
Considering that in general, most vehicle owners choose to move a target vehicle after receiving prompt information about stopping, in this embodiment, the record of stopping of the target vehicle can be released when the stopping time in the stopping area is smaller than the stopping time threshold, so that the stopped vehicle in the set area can be effectively managed.
In one embodiment, as shown in fig. 4, according to parking information and parking space information in a set area, a method for sending parking prompt information to a terminal corresponding to a target vehicle includes:
Step S401: under the condition that parking spaces are established in a target zone according to parking information and parking space information in a set zone, acquiring parking time of a target vehicle in the target zone;
Step S402: determining parking cost according to parking time and parking rate of the parking space;
step S403: and sending parking prompt information to a terminal corresponding to the target vehicle according to the parking cost.
The parking rate of the parking space can be a rate corresponding to the parking space established in the target partition and can be determined according to information attributes such as the parking space property right and the like acquired in advance.
In one possible implementation manner, in the case that the target partition is determined to set up the time-limited parking space according to the parking information and the parking space information in the setting area, it may be determined that the target partition transitions from the attribute (or state) in which the parking space is set up to the attribute (or state) in which the parking space is not set up over time, the time may be calculated for the state in which the target area is in the state in which the parking space is set up and the state in which the parking space is not set up in the target area, respectively, and the recording operation is performed.
In view of the environment of semi-closed parking lots, there is a regional property problem that the entering vehicles cannot be charged in a comprehensive way, for example, the regions in the parking lot are the positions of gates of shops, and the shopkeeper can not charge for the entering vehicles and the alighting of the shopkeeper. Some are forbidden areas, and the forbidden events need to be reported. Conventional closed parking lots cannot meet this situation.
In this embodiment, on the basis of sending parking prompt information about forbidden parking when a parking space is not provided, according to the rate corresponding to the parking space, the parking prompt information is sent to the terminal corresponding to the target vehicle, so that good prompt, auxiliary and recording effects are provided for paying parking fees for related users of the target vehicle, and the parking behavior of the users of the target vehicle is convenient while the management is convenient. When the embodiment of the disclosure is applied to the semi-closed parking lot, more effective parking management can be provided based on the situation that the parking permission conditions and the parking charge conditions of each area of the semi-closed parking lot are different.
In one embodiment, according to parking information and parking space information in a set area, a method for sending parking prompt information to a terminal corresponding to a target vehicle includes:
updating a parking record of the set area according to the parking information and the parking space information;
in the case of receiving a query request about a target vehicle, querying a target zone according to the query request and a parking record;
and sending parking prompt information about the target zone to a terminal corresponding to the target vehicle.
The above-described parking record regarding the set area may include information regarding vehicles parked in each zone within the set area, such as license plates, models, etc. Information of vehicles parked in each zone can be acquired through at least one of the first image or the second image.
In this embodiment, the parking guidance information about the target division may include at least one of a text description, an image description, positioning information, and navigation information about the position of the target division. The navigation information may be map navigation information, voice navigation information, or the like.
In the scene of semi-closed parking area, to the outdoor semi-closed parking area of great, need carry out parking stall level navigation, and traditional closed parking area hardly provides parking stall level navigation outdoor. In this embodiment, the target zone can be determined according to the parking record, and the user of the target vehicle can conveniently take out the vehicle after parking by sending the parking prompt information about the target zone to the user of the target vehicle, independent of the positioning information about the vehicle.
In one example of the present disclosure, the aforementioned first and second images may be acquired by a gateway camera (close-range camera) and a panoramic camera (far-range camera). The images acquired by the barrier cameras may be used to identify vehicle details and the images acquired by the panoramic cameras may be used to determine target zones for a particular vehicle stop. If desired, a plurality of barrier cameras and panoramic cameras may be provided. Through calibrating pixel positions corresponding to the same actual positions among cameras, vehicles entering a set area are tracked across the cameras, detail information captured on the barrier cameras is conducted to the panoramic cameras, the targets are continuously tracked on the panoramic cameras, and the overall scheme of capturing details of the barrier cameras and capturing events (including parking events, driving-away events and the like) by the panoramic cameras is realized through a cross-camera tracking technology.
The method has the advantages that the method can divide a plurality of subareas in a set area, each subarea can be provided with no parking space, limited parking spaces, charging parking spaces and free parking spaces, and the method is mainly used for solving the problem of business store gates in a semi-closed parking area, is convenient for timely loading and unloading goods by the vehicles of store houses and does not charge. The toll parking space can be a normal parking toll collection area. The partition without setting the parking space is a illegal parking partition, and the illegal parking data is reported when the parking time of the area exceeds a threshold value.
And establishing a 3D virtual model of the target vehicle through 3D modeling, and accurately judging the relation between the target and the region. And judging the parking space where the target vehicle is parked specifically through the 3D virtual model, and further, when the parking state in the parking space is changed, sending the parking change state to the platform in time.
If the semi-enclosed parking area is small, a panoramic camera may be provided in case photographing of the vehicle in the entire semi-enclosed parking area can be achieved using the panoramic camera. If the semi-enclosed parking area is too large, the panoramic camera can also increase along with the increase of the parking space, the panoramic camera can also realize target conduction through a trans-camera technology, and the conduction direction can be bidirectional (for example, a tracking signal which can be transmitted from a first camera to a target vehicle to a second camera and a tracking signal which can be transmitted from the second camera to the target vehicle to the first camera). When a target vehicle tracked by the panoramic camera or the close-range camera is parked in a parking area, the target is judged to be parked beyond a threshold time, and in-place data is sent, so that the semi-closed parking in-place is ensured to timely send a message, and further, the warning information is prevented from being sent to the passing vehicle.
In one embodiment, the parking information processing method further includes:
Acquiring a first image and a second image of the target vehicle again under the condition that the target vehicle leaves the target zone;
determining license plate information of the target vehicle according to at least one of the first image and the second image;
Searching a parking record of a target area in the parking records of a set area under the condition that license plate information indicates that a license plate of a target vehicle cannot be identified; the parking record of the target area is generated according to license plate information which indicates that a license plate can be identified when entering a set area;
When there is no content corresponding to the target vehicle during parking in the target area, alarm content is generated.
In this embodiment, the alarm content may be generated after the alarm information sending operation is performed, or may be used to display to related personnel when the parking record is queried later.
In the embodiment, the warning content can be timely generated under the condition that the license plate of the target vehicle is maliciously lost and blocked, so that the effective management of parking in the set area is realized.
When the target vehicle is driven into the set area, the detail information of the target vehicle can be obtained through a close-range camera of the gate, and the target vehicle is tracked through a panoramic camera. When a vehicle in a parking space leaves a vehicle, if the panoramic camera tracking process is not interrupted, the detail information is not lost all the time, if the detail information is lost due to shielding, camera outage and the like, when the vehicle runs to a barrier gate, the detail is supplemented through a cross-camera tracking technology, and the in-position record is queried. If the target vehicle is a vehicle with a position in the record, transmitting off-position information, if the target vehicle is not in the position in the record, comparing the target vehicle with vehicles without license plates blocked in the position in the record, and judging whether the target vehicle is the same vehicle or not by matching each parking position shot by the panoramic camera; if the vehicles are the same, sending alarm information about the detection result of the shielding number plate, and discarding the vehicles which are not the same.
The equipment timely records the parking state in the parking space so as to judge whether the vehicle is still in the parking lot or not according to the previous parking information after the equipment is powered off and powered on again by combining the panoramic camera, the vehicle is reserved in the parking lot, and the entering vehicle order is abandoned if the vehicle is not in the parking lot.
It can be seen that the disclosed examples may incorporate panoramic cameras, close-up cameras, and semi-enclosed parking lots to achieve full-automatic unmanned intervention. In one example, the parking information transmitting method includes a process as shown in fig. 5A, 5B, 5C, 5D. As shown first in fig. 5A, includes:
step S501: and (5) image acquisition. And after the first camera and the second camera arranged in the semi-closed parking lot are configured, image acquisition is carried out through the first camera and the second camera. The first camera may be a near-view camera, and the second camera may be a far-view camera. In the case where the first camera or the second camera is powered off for a long time, the process advances to step S509 shown in fig. 5B.
Step S502: and (3) carrying out target detection on the vehicle under the condition that power is not interrupted for a long time.
The present vehicle verification logic is performed when the yard detects a long power outage condition. Traversing the present vehicle, checking the parking space recorded by the vehicle, and determining whether the vehicle is still in the parking space or not through distant matching. When the vehicle is in the parking space, continuing to track the vehicle until the vehicle leaves; and if the vehicle is not in the parking space, the departure event is reissued for the entrance record.
Step S503: the vehicle is driven into the close-range camera, attributes such as a license plate of a vehicle are identified. When the vehicle appears in the close-range camera, license plate detection is carried out on the vehicle. And when the vehicle does not have information such as license plates, the tracking results of the cameras are combined to identify the vehicle information, and the information such as license plates is obtained.
Step S504: and tracking the target vehicle to obtain a tracking result. When the vehicle moves to the distant view camera, cross-camera tracking is performed, and the vehicle information is transferred to the next camera.
Step S505: 3D modeling is performed on the target vehicle. And judging parking behaviors according to the configuration, and calculating the parking position of the target vehicle according to the 3D information of the target vehicle.
When the target vehicle is stationary, 3D modeling is carried out on the target vehicle, the actual position of the target vehicle in the image is obtained, and according to the position, the vehicle parking behavior is determined by combining configuration information.
Step S506: in the case of the toll area, the parking position acquires the parking space number information according to the configuration (corresponding to the parking space information in the setting area in the foregoing embodiment), transmits the target vehicle approach information to the specified platform, and transmits the parking prompt information to the terminal (user terminal) where the target vehicle is located.
In this example, when the vehicle is parked in the toll area, the parking space number of the vehicle is recorded, and a vehicle approach event is transmitted. When the vehicle is parked in a free zone, no vehicle approach event is sent.
Step S507: the target vehicle is continuously tracked.
During continuous tracking, vehicle information is re-identified as the vehicle travels off the yard past the close-range camera.
Step S508: if it is determined that the vehicle is leaving based on data obtained by continuously tracking the target vehicle (corresponding to the tracking result of the foregoing embodiment), if it is determined that the target vehicle is free to park in the set area, parking prompt information about free to park is transmitted; if the target vehicle is determined to stop in the forbidden zone in the set area, processing records about forbidden stops and sending stopping prompt information about forbidden stops.
In this example, when the vehicle is parked in a no-stop zone of a no-stop period, the user is reminded to drive out of the zone as soon as possible by sending a no-stop warning. And sending out a stop violation alarm when the vehicle is stopped in the stop forbidden area for more than a specified time.
Further, if it is determined that the vehicle is leaving based on data obtained by continuously tracking the target vehicle (corresponding to the tracking result of the foregoing embodiment), if it is determined that the target vehicle is parked at a fee in the set area, the process shown in fig. 5C is entered.
As shown in fig. 5B, if a long power-down of the first camera or the second camera or other device affects normal tracking of the vehicle in the set area, the following steps are performed:
Step S509: and traversing the vehicle which is not leaving the field in the record of the entered position, and matching with the target vehicle.
Step S510: for each matching record (i.e. the in-position record), judging whether the corresponding vehicle is still in the original parking space, if not, proceeding to step S511; if yes, go to step S512.
Step S511: and compensating the record for the field operation. Namely, the corresponding entered position record is modified, and the information of the driving-away of the target vehicle is recorded.
Step S512: and continuously reserving the record of the entered position corresponding to the target vehicle.
Step S513: and when the departure of the target vehicle is detected, acquiring the vehicle information of the target vehicle through a close-range camera, and matching the vehicle in the record.
Step S514: and sending the departure event of the target vehicle to the designated terminal under the condition that the arrival record is matched.
Step S515: and discarding the off-site event of the target vehicle if the in-site record is not matched.
As shown in fig. 5C, if it is judged that the vehicle is leaving based on data obtained by continuously tracking the target vehicle (corresponding to the tracking result of the foregoing embodiment), if it is determined that the target vehicle is parked with a fee in the set area, the following steps are performed:
step S516: and acquiring license plate information of the target vehicle from the close-range camera, and matching the parked vehicles in the record.
Step S517: judging whether the license plate information has matched content in the record, if so, entering step S518; if not, the process proceeds to step S519.
Step S518: and sending a vehicle departure event, and ending the processing.
Step S519: judging whether a parking space in which the target vehicle is located before leaving exists in the record, if not, entering step S520; if yes, the process proceeds to step S521.
Step S520: discarding the target vehicle departure event.
Step S521: judging whether a vehicle in a parking space where a target vehicle leaves is provided with a license plate or not, if so, entering step S520; otherwise, step S522 is entered.
Step S522: judging whether license plate attributes of the target vehicle are absent; if yes, go to step S523; if not, the process proceeds to step S518.
Step S523: and sending an alarm for deliberately shielding the license plate.
As shown in fig. 5D, step S507 may further include:
step S5071: in the event that the target vehicle enters the other camera from the current camera, information of the target vehicle is transferred to the other camera, in which the target vehicle is tracked.
Step S5072: in the event that the target vehicle does not enter other cameras from the current camera, the target vehicle is tracked in the current camera.
As shown in fig. 5E, in a specific implementation manner, in step S508, if it is determined that the target vehicle is parked in the forbidden zone in the set area, the method processes the record about forbidden stop and sends a parking prompt message about forbidden stop, further includes:
Step S5081: and sending parking prompt information about forbidden parking to a terminal corresponding to the target vehicle under the condition that the target subarea where the target vehicle is parked within the parking time is the forbidden parking area (namely, the parking space is not set in the embodiment).
Step S5082: a record is generated regarding the disablement.
Step S5083: in the event that the target vehicle is detected to leave the target zone, determining whether a time for which the target vehicle is parked within the target zone exceeds a preset forbidden time threshold.
Step S5084: in the event that the time for which the target vehicle is parked within the target zone does not exceed the preset parking time threshold, the record concerning parking is released.
Step S5085: and sending the forbidden alarm information to the appointed platform under the condition that the time of the target vehicle stopping in the target zone exceeds the preset forbidden time threshold.
In this example, when the departure information of the target vehicle is identical to the information recorded by the vehicle tracking, the state of the target vehicle is judged: if the target vehicle is already in the record, sending an departure event; if the target vehicle is in the free parking area, the event may not be sent; and if the target vehicle has sent the illegal parking information, sending an illegal parking release alarm.
When the target vehicle has no tracking information, searching the current present vehicle according to the license plate number of the target vehicle, comparing the vehicles consistent with the license plate of the target vehicle, and sending out-of-field events.
When the target vehicle has tracking information but no license plate number is in the tracking information, firstly searching a vehicle in a record consistent with the license plate of the current target vehicle according to the license plate number of the target vehicle detected during off-site and sending an off-site event; if the vehicle is not found, matching the attribute and the image of the vehicle according to the tracking data, judging whether the entrance of the vehicle is license plate-free or not according to the matching consistency, if so, judging that the vehicle has a suspected license plate shielding intentional, and sending an intentional license plate shielding alarm; otherwise, an departure event is sent.
In one example, fig. 6A is a far view camera view, fig. 6B is a near view camera view, and fig. 6A and 6B include a first vehicle 601 and a second vehicle 602. When the vehicles tracked by the near-view camera enter the far-view camera, information transmission is carried out, and tracked information is transmitted to the far-view camera. The method comprises the steps of tracking and analyzing a distant view camera to enable a vehicle to stop stably, acquiring the position of the vehicle in an actual coordinate system according to a 3D virtual model of the vehicle and combining a calibration relation between the distant view camera and a close view camera, and judging the stopping behavior of the vehicle according to the regional setting of the distant view camera. Fig. 6C is a schematic diagram of a projected pattern 601 of a first vehicle and a projected pattern 602 of a second vehicle obtained by projecting the one vehicle in fig. 6A, 6B into a two-dimensional plane.
In general, most closed parking lots are slower in vehicle traffic than semi-closed parking lots, and require a certain labor cost for management. And the gates and the like require regular maintenance. The existing semi-closed parking lot schemes are mostly based on radar, are high in cost and visual, and are relatively large in required equipment for a large-scale semi-closed parking lot. And the problems of title disputes and parking space level navigation are difficult to deal with.
By the aid of the method and the device, accurate charging of the semi-closed parking area in blocks and time layering can be achieved on the basis of the high-order panoramic camera and the bayonet camera, title and charging disputes are avoided, event sending can be achieved immediately when entering the parking area, instantaneity is high, and adaptability is high.
The embodiment of the disclosure further provides a parking prompt device, as shown in fig. 7, including:
A tracking result obtaining module 701, configured to, when it is determined that the target vehicle enters the set area, perform position tracking on the target vehicle according to the first image and the second image of the target vehicle, and obtain a tracking result; the first image and the second image are obtained by shooting different ranges around the target vehicle, and the pixel positions corresponding to at least one same position point in the first image and the second image have a calibrated association relationship;
a parking information obtaining module 702, configured to obtain parking information of the target vehicle when it is determined that the target vehicle is parked in the set area according to the tracking result;
And the parking prompt information sending module 703 is configured to send parking prompt information to a terminal corresponding to the target vehicle according to the parking information and the parking space information in the set area.
In one embodiment, as shown in fig. 8, the dock information includes a target partition where a dock is located, and the dock information obtaining module includes:
a virtual model unit 801, configured to generate a corresponding virtual model in the first image or the second image according to the target vehicle;
And a target zone unit 802, configured to determine, according to the virtual model, a target zone in which a parking position of the target vehicle in the set area is located.
In one embodiment, the virtual model is a three-dimensional virtual model; the target partition unit is also to:
determining a projection graph of the target vehicle in a set area according to the three-dimensional virtual model;
and determining the target partition according to the overlapping proportion of the projection graph and each partition in the plurality of partitions contained in the set area.
In one embodiment, as shown in fig. 9, the parking guidance information transmission module includes:
The parking prohibition prompting information unit 901 is used for sending parking prohibition prompting information to a terminal corresponding to a target vehicle under the condition that a target subarea is determined to have no parking place according to parking information and parking place information in a set area;
and a parking forbidden recording unit 902, configured to update a parking record in the setting area according to the parking forbidden prompt information.
In one embodiment, as shown in fig. 10, the parking guidance apparatus further includes:
A parking time module 1001, configured to obtain a parking time of the target vehicle in the target zone when the target vehicle leaves the target zone;
a stop record release module 1002, configured to release the record about stop if the stop time is less than the set stop time threshold.
In one embodiment, as shown in fig. 11, the parking guidance information transmission module includes:
a parking time unit 1101, configured to obtain a parking time of a target vehicle in a target zone when it is determined that the target zone sets up a parking space according to the parking information and the parking space information in the set area;
a parking fee unit 1102 for determining a parking fee according to the parking time and the parking rate;
the first prompting unit 1103 is configured to send a parking prompting message to a terminal corresponding to the target vehicle according to the parking fee.
In one embodiment, as shown in fig. 12, the vehicle prompt information sending module includes:
A parking record updating unit 1201 for updating a parking record regarding the set area based on the parking information and the parking space information;
A query unit 1202 for querying the target zone according to the query request and the parking record in the case of receiving the query request about the target vehicle;
and the second prompting unit 1203 is used for sending parking prompting information about the target zone to the terminal corresponding to the target vehicle.
In one embodiment, as shown in fig. 13, the parking information processing apparatus further includes:
An image acquisition module 1301 for acquiring a first image and a second image of the target vehicle again in a case where the target vehicle leaves the target zone;
License plate information module 1302, configured to determine license plate information of the target vehicle according to at least one of the first image and the second image;
the license plate information searching module 1303 is used for searching a parking record of a target area in the parking records of a set area under the condition that license plate information indicates that a license plate of the target vehicle cannot be identified; the parking record of the target area is generated according to license plate information which indicates that a license plate can be identified when entering a set area;
The warning content generation module 1304 is configured to generate warning content when there is no content corresponding to the target vehicle during parking in the target area.
Fig. 14 is a main component of a system for performing a parking information processing method according to an example of the present disclosure, including an image acquisition module 1401, a system configuration module 1402, a parking analysis module 1403, and an information management module 1404. The functions of the respective modules shown in fig. 14 correspond to at least part of the functions of the respective modules of the parking information processing apparatus in the foregoing embodiments, and the image capturing module 1401, the system configuration module 1402, the parking analysis module 1403, and the information management module 1404 can realize the functions of the parking information processing apparatus of the foregoing embodiments.
The image acquisition module 1401 is configured to acquire images of vehicles at the entrance and the exit of the semi-closed parking lot by using a close-range camera, acquire information such as license plates, colors, types and the like of the vehicles, and determine a track of the vehicles by using a panoramic camera. The panoramic camera erection height is generally N (N is an integer greater than 0, such as 5 meters or more), and the near-field camera may not require the erection height.
A system configuration module 1402, configured to configure the system according to the usage scenario and requirements. The method specifically comprises the following steps:
Defining functional areas such as parking charging areas, forbidden parking areas and free parking areas;
setting time stages, namely setting different requirements, such as a free parking time period, a forbidden parking time period and a parking charging time period, for different time periods according to the requirements;
and the camera calibration configuration is carried out on a plurality of cameras, and the cameras are subjected to calibration configuration before being overlapped.
The parking analysis module 1403 is a core analysis module, and is configured to perform parking behavior analysis according to the pictures transmitted by the camera sensor and the configuration information.
When parking behavior analysis is performed, 3D modeling can be performed according to configuration, and a conversion matrix of two cameras needing to be associated in the first camera and the second camera can be obtained.
And detecting the vehicle according to the image acquired by the calibrated camera. And according to the vehicle detection result, performing vehicle behavior analysis.
The information management module 1404 is configured to enable the platform to receive entrance information, departure information, stop violation information, and the like of the vehicle. And sending the information to corresponding personnel to carry out corresponding notification according to the need, and calculating the parking time, the cost and the like according to the need.
In an example, the tracking result obtaining module 701, the parking information obtaining module 702, and the parking prompt information sending module 703 in fig. 7 may be disposed in the same device, such as the same server. In still another example, the tracking result obtaining module 701, the parking information obtaining module 702, and the parking prompt information sending module 703 in fig. 7 may be provided in different devices, such as shown in fig. 15, the recognition host 1501 in fig. 15 may be provided with the tracking result obtaining module 701 and the parking information obtaining module 702 in the foregoing embodiment, the tracking result obtaining module 701 in the recognition host 1501 may be connected to a first camera and a second camera, so as to perform position tracking on the target vehicle according to the first image and the second image of the target vehicle when it is determined that the target vehicle enters the set area, and obtain a tracking result, and the parking information obtaining module 702 in the recognition host 1501 is used to obtain the parking information of the target vehicle when it is determined that the target vehicle is parked in the set area according to the tracking result. The front-end platform 1503 may be provided with a parking prompt message sending module 703; the prompt information sending module 703 in the front end platform 1503 may obtain the parking information of the target vehicle obtained by the parking information obtaining module 702 in the identifying host 1501, where the prompt information sending module 703 in the front end platform 1503 is configured to send parking prompt information to a terminal corresponding to the target vehicle according to the parking information and the parking space information in the setting area. It should be understood that communication between the hint information sending module 703 in the front-end platform 1503 and the dock information obtaining module 702 in the identification host 1501 may be via the internet. The parking information obtaining module 702 in the front-end platform 1503 may send parking prompt information to a terminal corresponding to the target vehicle; specifically, the parking information obtaining module 702 in the front-end platform 1503 may send parking prompt information to a terminal (illustrated as a user in fig. 15) corresponding to the target vehicle through a cloud server. In addition, the aforementioned parking record of the target area generated from the parking guidance information may be stored in the storage device 1502 shown in fig. 15.
In the technical scheme of the disclosure, the acquisition, storage, application and the like of the related user personal information all conform to the regulations of related laws and regulations, and the public sequence is not violated.
According to embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.
Fig. 16 illustrates a schematic block diagram of an example electronic device 1600 that can be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 16, the electronic device 1600 includes a computing unit 1601 that can perform various suitable actions and processes according to a computer program stored in a Read Only Memory (ROM) 1602 or a computer program loaded from a storage unit 1608 into a Random Access Memory (RAM) 1603. In the RAM 1603, various programs and data required for the operation of the electronic device 1600 may also be stored. The computing unit 1601, ROM 1602, and RAM 1603 are connected to each other by a bus 1604. An input/output (I/O) interface 1605 is also connected to the bus 1604.
Various components in electronic device 1600 are connected to I/O interface 1605, including: an input unit 1606 such as a keyboard, a mouse, and the like; an output unit 1607 such as various types of displays, speakers, and the like; a storage unit 1608, such as a magnetic disk, an optical disk, or the like; and a communication unit 1609, such as a network card, modem, wireless communication transceiver, or the like. The communication unit 1609 allows the electronic device 1600 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunications networks.
The computing unit 1601 may be a variety of general purpose and/or special purpose processing components with processing and computing capabilities. Some examples of computing unit 1601 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 1601 performs the above-described parking prompting method. For example, in some embodiments, the above-described parking hint methods may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as the storage unit 1608. In some embodiments, some or all of the computer programs may be loaded and/or installed onto electronic device 1600 via ROM 1602 and/or communication unit 1609. When a computer program is loaded into RAM 1603 and executed by computing unit 1601, one or more steps of the parking guidance method described above may be performed. Alternatively, in other embodiments, the computing unit 1601 may be configured to perform the above-described parking hint method by any other suitable means (e.g. by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. These program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus such that the program code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the internet.
The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server incorporating a blockchain.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps recited in the present disclosure may be performed in parallel, sequentially, or in a different order, provided that the desired results of the disclosed aspects are achieved, and are not limited herein.
The above detailed description should not be taken as limiting the scope of the present disclosure. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present disclosure are intended to be included within the scope of the present disclosure.