CN110533923B - Parking management method and device, computer equipment and storage medium - Google Patents
Parking management method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110533923B CN110533923B CN201910820712.0A CN201910820712A CN110533923B CN 110533923 B CN110533923 B CN 110533923B CN 201910820712 A CN201910820712 A CN 201910820712A CN 110533923 B CN110533923 B CN 110533923B
- Authority
- CN
- China
- Prior art keywords
- point cloud
- data
- cloud data
- parking
- image frame
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07B—TICKET-ISSUING APPARATUS; FARE-REGISTERING APPARATUS; FRANKING APPARATUS
- G07B15/00—Arrangements or apparatus for collecting fares, tolls or entrance fees at one or more control points
- G07B15/02—Arrangements or apparatus for collecting fares, tolls or entrance fees at one or more control points taking into account a variable factor such as distance or time, e.g. for passenger transport, parking systems or car rental systems
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/04—Detecting movement of traffic to be counted or controlled using optical or ultrasonic detectors
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/042—Detecting movement of traffic to be counted or controlled using inductive or magnetic detectors
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/123—Traffic control systems for road vehicles indicating the position of vehicles, e.g. scheduled vehicles; Managing passenger vehicles circulating according to a fixed timetable, e.g. buses, trains, trams
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/14—Traffic control systems for road vehicles indicating individual free spaces in parking areas
- G08G1/141—Traffic control systems for road vehicles indicating individual free spaces in parking areas with means giving the indication of available parking spaces
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/14—Traffic control systems for road vehicles indicating individual free spaces in parking areas
- G08G1/145—Traffic control systems for road vehicles indicating individual free spaces in parking areas where the indication depends on the parking areas
- G08G1/147—Traffic control systems for road vehicles indicating individual free spaces in parking areas where the indication depends on the parking areas where the parking area is within an open public zone, e.g. city centre
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/14—Traffic control systems for road vehicles indicating individual free spaces in parking areas
- G08G1/145—Traffic control systems for road vehicles indicating individual free spaces in parking areas where the indication depends on the parking areas
- G08G1/148—Management of a network of parking areas
Abstract
The invention discloses a parking management method and device, computer equipment and a storage medium, relates to the technical field of video monitoring, and is used for improving the snapshot precision of a parking product. The main technical scheme of the invention is as follows: acquiring point cloud data of a radar monitoring area and image frame data shot by camera equipment according to a preset time interval; establishing a two-dimensional coordinate corresponding to the point cloud data; determining the positions of the parking events in the two-dimensional coordinates according to the point cloud data, and identifying the positions of the parking events in the image frame data from the image frame data; back projecting the point cloud data in the two-dimensional coordinate system onto the image frame data; acquiring a parking event with coincident point cloud data and position data in image video frame data; and shooting license plate information of the vehicle corresponding to the parking event with the point cloud data and the position data superposed through a camera, and recording the stopping starting time of the vehicle.
Description
Technical Field
The invention relates to the technical field of intelligent traffic, in particular to a parking management method, a parking management device, computer equipment and a storage medium.
Background
With the increase of vehicles, the traffic volume of cities is increased continuously, and the traffic jam is more frequent. Road traffic jam caused by illegal parking is particularly serious, if the road traffic jam is not discovered and eliminated in time, once an accident occurs, the traffic jam is caused, and the normal traffic capacity of the road is seriously influenced. At present, a plurality of places adopt parking modes of road parking spaces, the problems of difficult parking and the like are relieved to a certain extent, and the opportunities are created for traffic jam. Therefore, how to effectively manage the urban public parking spaces is very important.
At present, a method based on high-level video manages parked vehicles, and the method realizes intelligent supervision of parking spaces by utilizing an artificial intelligence algorithm, so that driving test parking spaces can be effectively managed. However, the method based on high-order video has the following problems: the remote place from the camera cannot be effectively monitored, and the utilization rate of the equipment is low; the parking space state judgment is inaccurate due to the fact that the surrounding environment is complex and the weather is severe, and the precision of the parking product snapshot is reduced.
Disclosure of Invention
The invention provides a parking management method, a parking management device, computer equipment and a storage medium, which are used for improving the snapshot precision of a parking product.
The embodiment of the invention provides a parking management method, which comprises the following steps:
acquiring point cloud data of a radar monitoring area and image frame data shot by camera equipment according to a preset time interval; establishing a two-dimensional coordinate corresponding to the point cloud data;
determining the occurrence of a parking event and the position of the parking event in the two-dimensional coordinate according to the point cloud data, and identifying the occurrence of the parking event and the position data of the parking event in the image frame data from the image frame data;
back projecting the point cloud data in the two-dimensional coordinate system onto the image frame data; acquiring a parking event with coincident point cloud data and position data in the image video frame data;
and shooting license plate information of a vehicle corresponding to the parking event with the point cloud data and the position data superposed through the camera equipment, and recording the stopping starting time of the vehicle.
The embodiment of the invention provides a parking management device, which comprises:
the acquisition module is used for acquiring point cloud data of a radar monitoring area and image frame data shot by the camera equipment according to a preset time interval; establishing a two-dimensional coordinate corresponding to the point cloud data;
the identification module is used for determining the occurrence of a parking event and the position of the parking event in the two-dimensional coordinate according to the point cloud data, and identifying the occurrence of the parking event and the position data of the parking event in the image frame data from the image frame data;
the back projection module is also used for back projecting the point cloud data in the two-dimensional coordinate system onto the image frame data;
the acquisition module is further used for acquiring a parking event with coincident point cloud data and position data in the image video frame data;
and the shooting and recording module is used for shooting the license plate information of the vehicle corresponding to the parking event with the point cloud data and the position data superposed through the camera equipment and recording the stopping starting time of the vehicle.
A computer device comprising a memory, a processor and a computer program stored in said memory and executable on said processor, said processor implementing the parking management method when executing said computer program.
A computer-readable storage medium, which stores a computer program that, when executed by a processor, implements the parking management method described above.
The invention provides a parking management method, a parking management device, computer equipment and a storage medium.A point cloud data of a radar monitoring area and image frame data shot by camera equipment are firstly obtained according to a preset time interval; establishing a two-dimensional coordinate corresponding to the point cloud data; then determining the position of the parking event and the parking event in the two-dimensional coordinate according to the point cloud data, and identifying the position data of the parking event and the parking event in the image frame data from the image frame data; back projecting the point cloud data in the two-dimensional coordinate system onto the image frame data; acquiring a parking event with coincident point cloud data and position data in image video frame data; and shooting license plate information of the vehicle corresponding to the parking event with the point cloud data and the position data superposed through a camera, and recording the stopping starting time of the vehicle. Compared with the prior art that the parking space is intelligently monitored by using an artificial intelligence algorithm, the method determines whether a corresponding parking event occurs or not through point cloud data and image frame data, namely, an event that point cloud data and position data coincide in the same coordinate system is determined as the parking event, and shoots the license plate information of a vehicle corresponding to the parking event through the camera equipment and records the stopping starting time of the vehicle. Because the radar has all weather and long distance and has good anti-jamming capability to severe weather, the invention can accurately determine the occurrence of the parking event through the point cloud data and the position data, thereby improving the snapshot precision of the parking product through the invention.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments of the present invention will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without inventive labor.
FIG. 1 is a diagram illustrating an application environment of a parking management method according to an embodiment of the present invention;
FIG. 2 is a flowchart of a parking management method according to an embodiment of the present invention;
FIG. 3 is a schematic view of an embodiment of the present invention illustrating the installation of a radar and camera device;
FIG. 4 is a schematic diagram of the time synchronization of data collected by a radar and a camera device according to an embodiment of the present invention;
FIG. 5 is a flow chart of determining a parking event from point cloud data in accordance with an embodiment of the present invention;
FIG. 6 is a flow chart of backprojecting point cloud data to image frame data in an embodiment of the present invention;
FIG. 7 is a schematic diagram of a camera coordinate transformation to pixel coordinates according to an embodiment of the invention;
FIG. 8 is a schematic diagram illustrating data association between a radar and an image capture device according to an embodiment of the present invention;
FIG. 9 is a functional block diagram of a parking management apparatus in accordance with an embodiment of the present invention;
FIG. 10 is a schematic diagram of a computer device according to an embodiment of the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The parking management method provided by the application can be applied to the application environment shown in fig. 1, wherein the camera device and the radar are communicated with the server through a network. The server acquires point cloud data of a radar monitoring area and image frame data shot by the camera equipment according to a preset time interval; establishing a two-dimensional coordinate corresponding to the point cloud data; determining the positions of the parking events in the two-dimensional coordinates according to the point cloud data, and identifying the positions of the parking events in the image frame data from the image frame data; back projecting the point cloud data in the two-dimensional coordinate system onto the image frame data; acquiring a parking event with coincident point cloud data and position data in image video frame data; and shooting license plate information of the vehicle corresponding to the parking event with the point cloud data and the position data superposed through a camera, and recording the stopping starting time of the vehicle. The computer device may be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, among others. The server may be implemented as a stand-alone server or as a server cluster consisting of a plurality of servers.
In an embodiment, as shown in fig. 2, a parking management method is provided, which is described by taking the application of the method to the server in fig. 1 as an example, and includes the following steps:
s10, acquiring point cloud data of a radar monitoring area and image frame data shot by the camera equipment according to a preset time interval; and establishing a two-dimensional coordinate corresponding to the point cloud data.
As shown in the installation diagram of the radar and the camera device shown in fig. 3, the installation angle of the radar and the camera device is overlooked in the parking space, the opposite side of the roadside parking space is placed, the same side can also be installed, the installation height is about 5m, the installation position of the camera device is close to 0 relative to the radar, the rolling angle of the camera is close to 0, and the pitching angle and the heading angle of the camera device are adjusted, so that the radar radiation angle and the view angle of the camera device cover the parking space.
It should be noted that, in the embodiment of the present invention, the positions of the radar and the camera device are fixed, so that the picture captured by the camera device is a video picture with a fixed angle, then, region division needs to be performed on the video picture with the fixed angle, the video picture is divided into specific parking spaces, and coordinates corresponding to parking violation regions in the video picture are respectively configured, so as to configure corresponding parking spaces and/or parking violation regions for each position in the image frame data; the point cloud data in the radar monitoring area correspond to points in the two-dimensional coordinate system one by one, and different parking spaces and illegal parking areas are configured for the point cloud data of different position areas in the radar monitoring area.
The preset time interval in the embodiment of the present invention may be set according to actual requirements, such as 1 second, 2 seconds, 3 seconds, and the like, and the embodiment of the present invention is not limited specifically. In the embodiment of the invention, a two-dimensional coordinate corresponding to point cloud data is established, namely a radar two-dimensional coordinate system is established by taking a radar as an origin, and the point cloud data in a radar monitoring area corresponds to points in the two-dimensional coordinate one by one; and point cloud data of different position areas in the radar monitoring area are configured into different parking spaces and illegal parking areas, and are calibrated in a two-dimensional coordinate.
As shown in fig. 4, the sensors of the camera device and the radar need to be synchronized in time, the frequency of acquiring data by the radar and the camera device is acquired, the sensor with the lowest frequency is taken as a time reference, the frequency of checking radar data is 14-16 hertz (Hz), and the frequency of checking radar data is 30 Hz, so that when the message of point cloud data is refreshed each time, image frame data of a current frame is recorded, and common sampling is completed, thereby ensuring the synchronization of the image acquisition data of the radar and the camera device in time.
S20, determining the parking event and the position of the parking event in the two-dimensional coordinate according to the point cloud data; and identifying the parking event and the position data of the parking event in the image frame data from the image frame data.
Specifically, as shown in fig. 5, determining the parking event and the position of the parking event in the two-dimensional coordinate according to the point cloud data includes:
s201, detecting whether the point cloud data exist for a period of time.
The storage period in the embodiment of the present invention may be set according to actual requirements, and specifically may be 2 minutes, 3 minutes, 5 minutes, and the like, and the embodiment of the present invention is not specifically limited.
S202, if the point cloud data stored for a period of time exists, determining the point cloud data stored for a period of time as the occurring parking event.
In the embodiment of the invention, different parking spaces and illegal parking areas correspond to different point cloud data, so that a specific parking event at a certain position can be determined through the point cloud data corresponding to the different parking spaces and illegal parking areas, for example, the point cloud data of the position 1 corresponding to the No. 1 parking space, and after the point cloud data of the position 1 is determined to exist for a period of time, the parking event at the No. 1 parking space can be determined.
It should be noted that, in the actual parking process, there may be a situation of parking in an illegal parking area, so the embodiment of the present invention sets two different durations for a parking space and an illegal parking area, so as to avoid a situation that a vehicle is mistakenly regarded as illegal parking due to temporary parking. Specifically, after point cloud data of a radar monitoring area is acquired according to a preset time interval, a parking space and/or an illegal parking area corresponding to the point cloud data is determined to exist, if the point cloud data corresponds to the parking space, whether the duration of the point cloud data is larger than a first threshold value is judged, and if the duration of the point cloud data is larger than the first threshold value, the parking space can be determined to be occupied; if the point cloud data corresponds to an illegal parking area, whether the existence time of the point cloud data is larger than a second threshold value or not is judged, if so, the illegal parking area can be determined to be occupied, wherein the first threshold value is smaller than the second threshold value, and the specific numerical value can be set according to the actual situation.
S203, marking the parking event in the two-dimensional coordinate system according to the position of the point cloud data stored for a period of time.
According to the embodiment of the invention, the returned signal is monitored by the installed radar, the point cloud data of the monitored area can be obtained in real time, after the radar is installed and fixed, the radar monitored area is fixed, the point cloud data in the radar monitored area can be in one-to-one correspondence in the two-dimensional coordinate system established by taking the radar as the origin, and vehicles temporarily parked can appear in the actual scene, so that after the point cloud data is obtained, whether the point cloud data is stored for a period of time needs to be further judged, and the point cloud data stored for a period of time is marked in the two-dimensional coordinate system, so that the point cloud data of the vehicles temporarily parked is prevented from being calibrated, and the accuracy of parking event determination in the subsequent steps is improved.
In one embodiment of the present invention, identifying the parking event and the position data of the parking event in the image frame data from the image frame data includes: extracting a parking event from the image frame data according to a deep learning model, and performing regression and identification on the parking event to obtain a pixel rectangular boundary frame of the parking event; a rectangular bounding box of pixels of the parking event is marked in the image frame data. Specifically, after image frame data is acquired, preprocessing operation needs to be performed on the image frame data, then a parking event is extracted from an image interesting region by using an off-line model trained through deep learning, position regression and recognition are performed on the parking event, a pixel rectangular boundary box of the parking event is acquired, and then the pixel rectangular boundary box of the parking event is marked in the image frame data.
S30, back projecting the point cloud data in the two-dimensional coordinate system onto the image frame data; and a parking event is acquired that coincides with the position data in the image video frame data.
In one embodiment of the present invention, as shown in fig. 6, the step S30 of back-projecting the point cloud data in the two-dimensional coordinate system onto the image frame data includes:
s301, establishing a world coordinate system with the camera equipment as a center; and transferring the point cloud data in the two-dimensional coordinates to the world coordinate system.
The X and Y coordinate information of the target can be obtained through the point cloud data, and the z coordinate information of the target does not exist, so that the conversion from the point cloud data coordinate system Or to the world coordinate system Ow can be regarded as the conversion of a two-dimensional X-Y coordinate system, and the relationship between the Or and the Ow is not limited to translation and rotation.
And S302, converting the coordinates of the world coordinate system into a camera coordinate system.
In the embodiment of the invention, after the point cloud data coordinates are converted into the world coordinate system, the point cloud data coordinates are converted into pixel coordinates. Because the obtained world coordinate values are two-dimensional, only have x and y values and no z value, the world coordinate values can be given by using priori knowledge, the world coordinate system is converted into a camera coordinate system, and the camera coordinate is converted into a pixel coordinate.
And S303, converting the coordinates of the camera coordinate system to a coordinate system corresponding to the image frame data.
FIG. 7 is a schematic diagram of the transformation of camera coordinates to pixel coordinates, i.e., the transformation of the coordinates of the camera coordinate system to the coordinate system corresponding to the image frame data, the pitch angle α, the heading angle β, the height h of the camera from the ground, the horizontal pixel value u, the vertical pixel value v, and the horizontal focal length f of the camera image in FIG. 7uFocal length f in the vertical directionvHorizontal principal point position C of principal point of camera imageuPrincipal point position C in the vertical directionvWorld coordinate systemgP, target horizontal coordinate position x of world coordinate systemgLongitudinal position ygTransformation of world coordinate system into image coordinate system matrixMatrix of pixel coordinate systemiP, then there is
The method comprises the steps of finding a relatively open and clean scene, placing a metal plate in front, moving the metal plate to a size which is as small as possible in a radar recognition range, and performing back projection on point cloud data of a radar detection target to match with image information of the camera.
gP＝{xg,yg,-h,1}
iP＝{u,v,1,1}
In an embodiment provided by the present invention, the acquiring a parking event in which point cloud data and position data coincide in the image video frame data includes: calculating the Euclidean distance between each point in the point cloud data and the midpoint of the pixel rectangular bounding box; determining points belonging to the same cluster in the point cloud data and the pixel rectangular bounding box according to the Euclidean distance calculation result; and determining that the parking events corresponding to the same cluster are the events of coincidence of the point cloud data and the position data.
Specifically, each point in the point cloud data is matched with a point of a pixel rectangular bounding box according to a nearest data association algorithm, and the target cost value is the mostSmall methods register. The method comprises the following specific steps: establishing a point cloud data and position data association gate, namely an association area of matching of the radar point cloud cluster and pixels in a pixel rectangular boundary frame of a target, as shown in fig. 8, wherein a1 is shown in the figure, a2 represents image data, B1, B2 and B3 represent point cloud data, and determining an association threshold: a rectangular correlation gate, an elliptical correlation gate; calculating corresponding near points of each point in the point cloud data in the image target pixel rectangular bounding box point set, namely calculating Euclidean distance as a target data association function of the two points
And establishing a pixel point and point cloud data association matrix in a pixel rectangular bounding box to form a data matching association pair, wherein camera detection A1 and radar B2 are matched to form the same target, and A2 and B3 are the same target.
And S40, shooting license plate information of the vehicle corresponding to the parking event with the point cloud data and the position data superposed through a camera, and recording the stopping starting time of the vehicle.
The camera device can be a high-definition spherical camera, and the spherical camera focused can be rotated through the high-definition spherical camera to capture detailed information such as license plates. In the embodiment of the present invention, the license plate information includes a license plate number, and details of the vehicle, such as information of a license plate, a vehicle type, a vehicle body color, a vehicle type, and the like, which is not specifically limited in the embodiment of the present invention.
Compared with the prior art that the parking management method realizes the intelligent monitoring of the parking spaces by using an artificial intelligence algorithm, the parking management method determines whether a corresponding parking event occurs or not through point cloud data and image frame data, namely, an event that point cloud data and position data coincide in the same coordinate system is determined as the parking event, and the image pickup equipment is used for shooting the license plate information of a vehicle corresponding to the parking event and recording the stop starting time of the vehicle. Because the radar has all weather and long distance and has good anti-jamming capability to severe weather, the invention can accurately determine the occurrence of the parking event through the point cloud data and the position data, thereby improving the snapshot precision of the parking product through the invention.
In an embodiment provided by the present invention, if there is no parking event in which the point cloud data and the position data coincide in the image video frame data, sending a radar and/or camera device position change warning message to a background manager, so that the background manager adjusts the radar and/or camera device to an originally set position. For example, the point cloud data can determine that the parking space No. 1 is a vehicle occupation area, the position of the parking space No. 1 corresponding to the image video frame data does not show that the parking space is occupied by the vehicle, but shows that the parking space is occupied by the vehicle at the position of the parking space No. 2 in the image video frame data, namely, after the point cloud data is back-projected to the image frame data, the point cloud data and the position data are not overlapped, at this time, it can be confirmed that the vehicle occupation area determined by the point cloud data stored for a period of time is not the same area as the vehicle occupation area determined by the image video frame data, which indicates that the monitoring position of the radar or the wide-view camera device is changed, and at this time, a background manager needs to be notified to adjust the positions of the radar and the wide.
In an embodiment provided by the present invention, the image capturing device captures license plate information of a vehicle corresponding to a parking event in which point cloud data and position data coincide, and records a stop start time of the vehicle, and the method further includes: when the parking event that point cloud data and position data coincide in the image video frame data disappears, judging whether a vehicle corresponding to the parking event shot by the camera device leaves or not; if the vehicle leaves, recording the stop ending time of the vehicle; and calculating the parking fee of the vehicle according to the stopping starting time and the stopping ending time of the vehicle.
In one embodiment provided by the invention, the parking space information near the owner can be accurately obtained for the owner, and the guided parking is carried out according to the parking space information. After the parking event with the coincident point cloud data and position data in the image video frame data is determined as the vehicle occupation area, the number of the vehicle idle areas is calculated according to the total number of the vehicle areas and the number of the vehicle occupation areas, and the number of the vehicle idle areas is sent to the vehicle owner client side in the preset range, so that the vehicle owner client side can obtain the available state of the nearby parking space. It should be noted that, in the embodiment of the present invention, before sending the total vehicle occupied area and the total vehicle free area to the vehicle owner client in the preset range, it is further required to obtain parking request information sent by the vehicle owner client in the preset range, and then send the number of vehicle free areas to the vehicle owner client in the preset range, which has sent the parking request, so that the vehicle owner client obtains the available state of the nearby parking space, thereby facilitating the parking of the user at the vehicle owner client.
Specifically, after a user vehicle drives into a parking space, the parking of the vehicle is detected, then the gun and ball linkage integral camera is dispatched according to the detected position information, a ball machine module of the camera is used for further capturing the license plate information of the vehicle, then information data such as parking space occupation condition and parking starting time of the vehicle are recorded, and a user parking record is generated. After a user drives a vehicle and leaves a parking space, the vehicle is detected to leave, information such as parking space state and leaving time is obtained, so that the server can calculate parking time and corresponding cost of the user, fee deduction is carried out from a parking account of the user, parking fee payment information is sent to the user, and the user can finish the fee payment process only by clicking to confirm payment after receiving the information. In addition, if abnormal parking is monitored at the roadside, reminding or warning information is sent to a client of a field manager, the manager receives a task instruction to carry out field inspection, photographs the violation behaviors for evidence obtaining and carries out punishment according to relevant regulations.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.
In one embodiment, a parking management device is provided, and the parking management device corresponds to the parking management method in the above embodiments one to one. As shown in fig. 9, the parking management apparatus includes an acquisition module 10, an identification module 20, a back projection module 30, and a photographing recording module 40. The functional modules are explained in detail as follows:
the acquisition module 10 is used for acquiring point cloud data of a radar monitoring area and image frame data shot by the camera equipment according to a preset time interval; establishing a two-dimensional coordinate corresponding to the point cloud data;
the identification module 20 is used for determining the occurrence of a parking event and the position of the parking event in the two-dimensional coordinates according to the point cloud data, and identifying the occurrence of the parking event and the position data of the parking event in the image frame data from the image frame data;
the back projection module 30 is further configured to back project the point cloud data in the two-dimensional coordinate system onto the image frame data;
the obtaining module 10 is further configured to obtain a parking event in which point cloud data and position data coincide in the image video frame data;
and the shooting and recording module 40 is used for shooting the license plate information of the vehicle corresponding to the parking event with the point cloud data and the position data superposed through the camera equipment and recording the stopping starting time of the vehicle.
Specifically, the back projection module 30 includes:
an establishing unit 31 for establishing a world coordinate system centered on the image pickup apparatus;
a conversion unit 32, configured to convert the point cloud data in the two-dimensional coordinates into the world coordinate system; converting coordinates of the world coordinate system to a camera coordinate system; and converting the coordinates of the camera coordinate system to a coordinate system corresponding to the image frame data.
Specifically, the identification module 20 includes:
a detection unit 21 configured to detect whether there is the point cloud data stored for a certain period of time;
the determining unit 22 is configured to determine the point cloud data stored for a certain period of time as an occurring parking event if the point cloud data stored for a certain period of time exists;
and the marking unit 23 is used for marking the occurred parking event in the two-dimensional coordinate system according to the position of the point cloud data stored for a period of time.
Further, the identification module 20 includes:
the determining unit 22 is further configured to extract a parking event from the image frame data according to a deep learning model, perform regression and recognition on the parking event, and obtain a rectangular pixel bounding box of the parking event;
the labeling unit 23 is further configured to label a rectangular bounding box of pixels of the parking event in the image frame data.
Specifically, the obtaining module 10 includes:
a calculating unit 11, configured to calculate an euclidean distance between each point in the point cloud data and a midpoint of the rectangular bounding box of the pixel;
a determining unit 12, configured to determine, according to the euclidean distance calculation result, points belonging to the same cluster in the point cloud data and the pixel rectangular bounding box; and determining that the parking events corresponding to the same cluster are the events of coincidence of the point cloud data and the position data.
Further, the apparatus further comprises:
and the sending module 50 is configured to send radar and/or camera device position change warning information to a background manager if a parking event that point cloud data and position data coincide does not exist in the image video frame data, so that the background manager adjusts the radar and/or camera device to an originally set position.
Further, the apparatus further comprises:
the shooting recording module 40 is further configured to, when it is determined that the parking event in which the point cloud data and the position data coincide with each other in the image video frame data disappears, shoot whether the vehicle corresponding to the parking event leaves according to the image capturing device; if the vehicle leaves, recording the stop ending time of the vehicle;
and the charging module 60 is configured to calculate the parking fee of the vehicle according to the stop starting time and the stop ending time of the vehicle.
Further, the apparatus further comprises:
the determining module 70 is further configured to determine a parking event in which the point cloud data and the position data coincide in the image video frame data as a vehicle occupation area;
the sending module 50 is further configured to calculate the number of vehicle idle areas according to the total number of vehicle areas and the number of vehicle occupied areas, and send the number of vehicle idle areas to an owner client within a preset range, so that the owner client obtains an available state of a nearby parking space.
For specific limitations of the parking management device, reference may be made to the above limitations of the parking management method, which are not described herein again. The modules in the parking management device can be wholly or partially realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 10. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a parking management method.
In one embodiment, a computer device is provided, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program:
acquiring point cloud data of a radar monitoring area and image frame data shot by camera equipment according to a preset time interval; establishing a two-dimensional coordinate corresponding to the point cloud data;
determining the occurrence of a parking event and the position of the parking event in the two-dimensional coordinate according to the point cloud data, and identifying the occurrence of the parking event and the position data of the parking event in the image frame data from the image frame data;
back projecting the point cloud data in the two-dimensional coordinate system onto the image frame data; acquiring a parking event with coincident point cloud data and position data in the image video frame data;
and shooting license plate information of a vehicle corresponding to the parking event with the point cloud data and the position data superposed through the camera equipment, and recording the stopping starting time of the vehicle.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring point cloud data of a radar monitoring area and image frame data shot by camera equipment according to a preset time interval; establishing a two-dimensional coordinate corresponding to the point cloud data;
determining the occurrence of a parking event and the position of the parking event in the two-dimensional coordinate according to the point cloud data, and identifying the occurrence of the parking event and the position data of the parking event in the image frame data from the image frame data;
back projecting the point cloud data in the two-dimensional coordinate system onto the image frame data; acquiring a parking event with coincident point cloud data and position data in the image video frame data;
and shooting license plate information of a vehicle corresponding to the parking event with the point cloud data and the position data superposed through the camera equipment, and recording the stopping starting time of the vehicle.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present invention, and are intended to be included within the scope of the present invention.
Claims (18)
1. A parking management method is applied to a server, and comprises the following steps:
acquiring point cloud data of a radar monitoring area and image frame data shot by camera equipment according to a preset time interval; establishing a two-dimensional coordinate corresponding to the point cloud data;
determining the occurrence of a parking event and the position of the parking event in the two-dimensional coordinate according to the point cloud data, and identifying the occurrence of the parking event and the position data of the parking event in the image frame data from the image frame data;
back projecting the point cloud data in the two-dimensional coordinate system onto the image frame data; acquiring a parking event with coincident point cloud data and position data in the image frame data;
and shooting license plate information of a vehicle corresponding to the parking event with the point cloud data and the position data superposed through the camera equipment, and recording the stopping starting time of the vehicle.
2. The method of claim 1, wherein back projecting the point cloud data in the two-dimensional coordinate system onto the image frame data comprises:
establishing a world coordinate system with the camera device as a center; and transferring the point cloud data in the two-dimensional coordinates to the world coordinate system;
converting coordinates of the world coordinate system to a camera coordinate system;
and converting the coordinates of the camera coordinate system to a coordinate system corresponding to the image frame data.
3. The method of claim 1, wherein the determining from the point cloud data the parking event occurred and the location of the parking event at the two-dimensional coordinates comprises:
detecting whether the point cloud data stored for a period of time exists;
if the point cloud data stored for a period of time exists, determining the point cloud data stored for a period of time as the occurring parking event;
and marking the occurred parking events in the two-dimensional coordinate system according to the positions of the point cloud data stored for a period of time.
4. The method of claim 1, wherein identifying from the image frame data the occurrence of a parking event and location data of the parking event in the image frame data comprises:
extracting a parking event from the image frame data according to a deep learning model, and performing regression and identification on the parking event to obtain a pixel rectangular boundary frame of the parking event;
a rectangular bounding box of pixels of the parking event is marked in the image frame data.
5. The method of claim 4, wherein said acquiring a parking event in which point cloud data and location data coincide in the image frame data comprises:
calculating the Euclidean distance between each point in the point cloud data and the midpoint of the pixel rectangular bounding box;
determining points belonging to the same cluster in the point cloud data and the pixel rectangular bounding box according to the Euclidean distance calculation result;
and determining that the parking events corresponding to the same cluster are the events of coincidence of the point cloud data and the position data.
6. The method of claim 1, further comprising:
and if the parking event that the point cloud data and the position data are coincident does not exist in the image frame data, sending radar and/or camera equipment position change warning information to a background manager so that the background manager can adjust the radar and/or camera equipment to the originally set position.
7. The method according to claim 1, wherein the image capturing device captures license plate information of a vehicle corresponding to a parking event in which the point cloud data and the position data coincide, and records a stop start time of the vehicle, and the method further comprises:
when the parking event that point cloud data and position data coincide in the image frame data disappears, judging whether a vehicle corresponding to the parking event shot by the camera device leaves or not;
if the vehicle leaves, recording the stop ending time of the vehicle;
and calculating the parking fee of the vehicle according to the stopping starting time and the stopping ending time of the vehicle.
8. The method of claim 7, further comprising:
determining a parking event in which point cloud data and position data coincide in the image frame data as a vehicle occupation region;
and calculating the number of the vehicle idle areas according to the total number of the vehicle areas and the number of the vehicle occupied areas, and sending the number of the vehicle idle areas to the owner client in a preset range so that the owner client can acquire the available state of the nearby parking spaces.
9. A parking management apparatus, characterized in that the apparatus comprises:
the acquisition module is used for acquiring point cloud data of a radar monitoring area and image frame data shot by the camera equipment according to a preset time interval; establishing a two-dimensional coordinate corresponding to the point cloud data;
the identification module is used for determining the occurrence of a parking event and the position of the parking event in the two-dimensional coordinate according to the point cloud data, and identifying the occurrence of the parking event and the position data of the parking event in the image frame data from the image frame data;
the back projection module is also used for back projecting the point cloud data in the two-dimensional coordinate system onto the image frame data;
the acquisition module is further used for acquiring a parking event with coincident point cloud data and position data in the image frame data;
and the shooting and recording module is used for shooting the license plate information of the vehicle corresponding to the parking event with the point cloud data and the position data superposed through the camera equipment and recording the stopping starting time of the vehicle.
10. The apparatus of claim 9, wherein the back projection module comprises:
an establishing unit configured to establish a world coordinate system centered on the image pickup apparatus;
the conversion unit is used for converting the point cloud data in the two-dimensional coordinates into the world coordinate system; converting coordinates of the world coordinate system to a camera coordinate system; and converting the coordinates of the camera coordinate system to a coordinate system corresponding to the image frame data.
11. The apparatus of claim 9, wherein the identification module comprises:
the detection unit is used for detecting whether the point cloud data which exist for a period of time exist or not;
the system comprises a determining unit, a judging unit and a judging unit, wherein the determining unit is used for determining point cloud data stored for a period of time as a parking event if the point cloud data stored for the period of time exists;
and the marking unit is used for marking the parking event in the two-dimensional coordinate system according to the position of the point cloud data stored for a period of time.
12. The apparatus of claim 9, wherein the identification module comprises:
the determining unit is further used for extracting a parking event from the image frame data according to a deep learning model, performing regression and recognition on the parking event and acquiring a pixel rectangular boundary frame of the parking event;
and the marking unit is also used for marking a pixel rectangular boundary box of the parking event in the image frame data.
13. The apparatus of claim 12, wherein the obtaining module comprises:
the calculation unit is used for calculating the Euclidean distance between each point in the point cloud data and the midpoint of the pixel rectangular bounding box;
the determining unit is used for determining the point cloud data and the points belonging to the same cluster in the pixel rectangular bounding box according to the Euclidean distance calculation result; and determining that the parking events corresponding to the same cluster are the events of coincidence of the point cloud data and the position data.
14. The apparatus of claim 9, further comprising:
and the sending module is used for sending radar and/or camera equipment position change warning information to a background manager if a parking event that the point cloud data and the position data are overlapped does not exist in the image frame data, so that the background manager can adjust the radar and/or the camera equipment to the originally set position.
15. The apparatus of claim 9, further comprising:
the shooting recording module is further used for shooting whether a vehicle corresponding to the parking event leaves according to the shooting equipment when the parking event that the point cloud data and the position data coincide in the image frame data disappears; if the vehicle leaves, recording the stop ending time of the vehicle;
and the charging module is used for calculating the parking fee of the vehicle according to the stopping starting time and the stopping ending time of the vehicle.
16. The apparatus of claim 15, further comprising:
the determining module is further used for determining a parking event with coincident point cloud data and position data in the image frame data as a vehicle occupation area;
and the sending module is also used for calculating the number of the vehicle idle areas according to the total number of the vehicle areas and the number of the vehicle occupied areas, and sending the number of the vehicle idle areas to the owner client in a preset range so that the owner client can acquire the available state of the nearby parking spaces.
17. A computer arrangement comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the parking management method according to any of claims 1 to 8 when executing the computer program.
18. A computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, carries out the parking management method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910820712.0A CN110533923B (en) | 2019-08-29 | 2019-08-29 | Parking management method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910820712.0A CN110533923B (en) | 2019-08-29 | 2019-08-29 | Parking management method and device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110533923A CN110533923A (en) | 2019-12-03 |
| CN110533923B true CN110533923B (en) | 2020-10-13 |
Family
ID=68665970
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910820712.0A Active CN110533923B (en) | 2019-08-29 | 2019-08-29 | Parking management method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110533923B (en) |
Families Citing this family (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111444845B (en) * | 2020-03-26 | 2023-05-12 | 江苏集萃华科智能装备科技有限公司 | Non-motor vehicle illegal stop recognition method, device and system |
| CN111582256A (en) * | 2020-04-26 | 2020-08-25 | 智慧互通科技有限公司 | Parking management method and device based on radar and visual information |
| CN111639765A (en) * | 2020-05-15 | 2020-09-08 | 视若飞信息科技(上海)有限公司 | Interaction method for using point track and detection domain |
| CN113763575B (en) * | 2020-06-03 | 2023-01-03 | 杭州海康威视数字技术股份有限公司 | Parking management system, method and device |
| CN111797734A (en) * | 2020-06-22 | 2020-10-20 | 广州视源电子科技股份有限公司 | Vehicle point cloud data processing method, device, equipment and storage medium |
| CN112489427B (en) * | 2020-11-26 | 2022-04-15 | 招商华软信息有限公司 | Vehicle trajectory tracking method, device, equipment and storage medium |
| CN112598925A (en) * | 2020-12-08 | 2021-04-02 | 北京精英路通科技有限公司 | Parking management method and device, computer equipment and storage medium |
| CN112541952A (en) * | 2020-12-08 | 2021-03-23 | 北京精英路通科技有限公司 | Parking scene camera calibration method and device, computer equipment and storage medium |
| CN112601049B (en) * | 2020-12-08 | 2023-07-25 | 北京精英路通科技有限公司 | Video monitoring method and device, computer equipment and storage medium |
| CN112883904B (en) * | 2021-03-15 | 2021-11-19 | 珠海安联锐视科技股份有限公司 | Method for detecting vehicle illegal parking lane occupation |
| CN113420805B (en) * | 2021-06-21 | 2022-11-29 | 车路通科技(成都)有限公司 | Dynamic track image fusion method, device, equipment and medium for video and radar |
| CN113920775B (en) * | 2021-10-13 | 2023-11-14 | 天津新泰基业电子股份有限公司 | Intelligent parking management operation method and system |
| CN114530056B (en) * | 2022-02-15 | 2023-05-02 | 超级视线科技有限公司 | Parking management method and system based on positioning information and image information |
| CN114360288A (en) * | 2022-03-21 | 2022-04-15 | 四川新迎顺信息技术股份有限公司 | AI-based garage management method, system, equipment and readable storage medium |
| CN114973752B (en) * | 2022-04-06 | 2023-12-22 | 深圳一清创新科技有限公司 | License plate and parking space number association method and device, intelligent vehicle and readable storage medium |
| CN115187732B (en) * | 2022-09-05 | 2022-12-23 | 江西省云眼大视界科技有限公司 | Image data acquisition and transmission device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107123303A (en) * | 2017-04-01 | 2017-09-01 | 智慧互通科技有限公司 | The system and method for radar and smart camera linkage management parking position |
| CN108710367A (en) * | 2018-05-23 | 2018-10-26 | 广州视源电子科技股份有限公司 | Laser data recognition methods, device, robot and storage medium |
| CN109214986A (en) * | 2017-07-03 | 2019-01-15 | 百度（美国）有限责任公司 | High-resolution 3-D point cloud is generated from the low resolution LIDAR 3-D point cloud and camera review of down-sampling |
| CN109253731A (en) * | 2018-08-06 | 2019-01-22 | 百度在线网络技术（北京）有限公司 | Parking space drawing generating method, device, equipment and readable storage medium storing program for executing |
| CN109712428A (en) * | 2019-02-27 | 2019-05-03 | 爱笔（北京）智能科技有限公司 | A kind of parking position localization method and device, system |
| CN109733284A (en) * | 2019-02-19 | 2019-05-10 | 广州小鹏汽车科技有限公司 | A kind of safety applied to vehicle, which is parked, assists method for early warning and system |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102010047162A1 (en) * | 2010-09-30 | 2012-04-05 | Valeo Schalter Und Sensoren Gmbh | Method and device for detecting free parking spaces |
| US10078790B2 (en) * | 2017-02-16 | 2018-09-18 | Honda Motor Co., Ltd. | Systems for generating parking maps and methods thereof |
| CN108921925B (en) * | 2018-06-27 | 2022-12-09 | 广州视源电子科技股份有限公司 | Semantic point cloud generation method and device based on laser radar and visual fusion |
-
2019
- 2019-08-29 CN CN201910820712.0A patent/CN110533923B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107123303A (en) * | 2017-04-01 | 2017-09-01 | 智慧互通科技有限公司 | The system and method for radar and smart camera linkage management parking position |
| CN109214986A (en) * | 2017-07-03 | 2019-01-15 | 百度（美国）有限责任公司 | High-resolution 3-D point cloud is generated from the low resolution LIDAR 3-D point cloud and camera review of down-sampling |
| CN108710367A (en) * | 2018-05-23 | 2018-10-26 | 广州视源电子科技股份有限公司 | Laser data recognition methods, device, robot and storage medium |
| CN109253731A (en) * | 2018-08-06 | 2019-01-22 | 百度在线网络技术（北京）有限公司 | Parking space drawing generating method, device, equipment and readable storage medium storing program for executing |
| CN109733284A (en) * | 2019-02-19 | 2019-05-10 | 广州小鹏汽车科技有限公司 | A kind of safety applied to vehicle, which is parked, assists method for early warning and system |
| CN109712428A (en) * | 2019-02-27 | 2019-05-03 | 爱笔（北京）智能科技有限公司 | A kind of parking position localization method and device, system |
Non-Patent Citations (2)
| Title |
|---|
| 一种基于线结构光的汽车侧位停车的环境感知方法;沈洁 等;《计算机与数字工程》;20190731(第7期);第1797-1804页 * |
| 基于激光反射率的点云与图像自动融合;赵玲娜 等;《测绘工程》;20170831;第26卷(第8期);第29-34页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110533923A (en) | 2019-12-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110533923B (en) | Parking management method and device, computer equipment and storage medium | |
| CN112509364B (en) | Method and device for determining parking state of vehicle, computer equipment and storage medium | |
| CN107305627B (en) | Vehicle video monitoring method, server and system | |
| CN110738150B (en) | Camera linkage snapshot method and device and computer storage medium | |
| CN110298300B (en) | Method for detecting vehicle illegal line pressing | |
| CN101770648B (en) | Video monitoring based loitering system and method thereof | |
| CN110491060B (en) | Robot, safety monitoring method and device thereof, and storage medium | |
| CN111860352B (en) | Multi-lens vehicle track full tracking system and method | |
| CN113470374A (en) | Vehicle overspeed monitoring method and device, computer equipment and storage medium | |
| CN111444798A (en) | Method and device for identifying driving behavior of electric bicycle and computer equipment | |
| CN111368615B (en) | Illegal building early warning method and device and electronic equipment | |
| CN112365719B (en) | Parking space management method and device, computer equipment and storage medium | |
| CN109615904A (en) | Parking management method, device, computer equipment and storage medium | |
| CN108847031A (en) | Traffic behavior monitoring method, device, computer equipment and storage medium | |
| US11580659B2 (en) | Method for size estimation by image recognition of specific target using given scale | |
| CN112597807A (en) | Violation detection system, method and device, image acquisition equipment and medium | |
| CN112601049B (en) | Video monitoring method and device, computer equipment and storage medium | |
| CN114255428A (en) | Vehicle parking identification method based on edge intelligence and roadside high-level monitoring video | |
| CN112733598A (en) | Vehicle law violation determination method and device, computer equipment and storage medium | |
| CN112598925A (en) | Parking management method and device, computer equipment and storage medium | |
| KR20210075533A (en) | Vision-based Rainfall Information System and Methodology Using Deep Learning | |
| CN114627409A (en) | Method and device for detecting abnormal lane change of vehicle | |
| CN110880205B (en) | Parking charging method and device | |
| CN110490117B (en) | Parking event determination method and system based on image depth information | |
| CN111914592B (en) | Multi-camera combined evidence obtaining method, device and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |