CN112382101B - Parking space management method and device, computer equipment and storage medium - Google Patents
Parking space management method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN112382101B CN112382101B CN202011204599.2A CN202011204599A CN112382101B CN 112382101 B CN112382101 B CN 112382101B CN 202011204599 A CN202011204599 A CN 202011204599A CN 112382101 B CN112382101 B CN 112382101B
- Authority
- CN
- China
- Prior art keywords
- parking space
- information
- vehicle
- target vehicle
- event
- 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
- 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
- G08G1/14—Traffic control systems for road vehicles indicating individual free spaces in parking areas
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
The patent discloses a parking space management method, a parking space management device, computer equipment and a storage medium, which relate to the field of intelligent transportation and are used for realizing intelligent supervision of parking spaces of small vehicles, effectively managing roadside berths, saving manpower resources and reducing the rate of missing orders. The main technical scheme of the invention is as follows: acquiring a video frame shot by the camera equipment, and identifying vehicles and pedestrians in the video frame by the algorithm module to acquire scene information; tracking the target vehicle in the scene information, and identifying vehicle characteristic information; combining the target vehicle information and the parking space information, and processing the target vehicle and related information in the parking space, wherein the processing comprises detecting a parking event, detecting a leaving event and updating the parking space information; and processing the related information of the empty parking space by combining the parking space information and the scene information, wherein the related information comprises detecting the leaving event and updating the parking space information.
Description
Technical Field
The invention relates to the field of intelligent transportation, in particular to a parking space management method and device, computer equipment and a storage medium.
Technical Field
With the social development, more and more families purchase automobiles, the traffic jam phenomenon is increasingly serious, more and more people select small-sized transportation tools such as storage battery cars, bicycles, motorcycles and the like to go out under the condition of medium-short distance traveling, special parking spaces for the small-sized transportation tools are set in part of cities, and the small-sized transportation tools have the characteristics of strong liquidity and large quantity, so that the parking spaces are effectively managed.
At present, the parking management system aiming at small-sized vehicles in the prior art is very lack, and the manual management is mainly used in the actual life. Because small-size vehicle mobility is stronger and quantity is many, current parking stall management system to the car can not directly be suitable for, produces the condition of lou single very easily. And small-size vehicle receives the sheltering from of other vehicles easily, and prior art scheme can not handle and shelter from the problem.
The scheme provides a parking space management method and device, computer equipment and a storage medium, intelligent supervision of parking spaces of small vehicles is achieved through an artificial intelligence algorithm, roadside parking spaces are effectively managed, manpower resources are saved, and the rate of missing orders is reduced.
Disclosure of Invention
The invention provides a parking space management method, a parking space management device, computer equipment and a storage medium, which are used for solving the parking space management problem of a small traffic tool for road test.
The embodiment of the invention provides a parking space management method, which comprises the following steps:
acquiring a video frame shot by a camera device, and identifying traffic tools and pedestrians in the video frame by an algorithm module to acquire scene information;
tracking a target vehicle in the scene information, and identifying vehicle characteristic information to form target vehicle information;
combining the target vehicle information and the parking space information, and processing the target vehicle and related information in the parking space, wherein the processing comprises detecting a parking event, detecting a leaving event and updating parking space information;
and processing the related information of the empty parking space by combining the parking space information and the scene information, wherein the related information comprises detecting the leaving event and updating the parking space information.
Optionally, the target vehicle is a small vehicle such as a battery car, a bicycle, or a motorcycle.
Optionally, the scene information includes coordinates of detection frames of the small vehicles, the automobiles and the pedestrians in the image, wherein the detection frames of the small vehicles include a whole automobile detection frame, a head detection frame and a tail detection frame.
Optionally, when processing the target vehicle and the related information in the parking space, firstly, judging whether a parking event is recorded in the parking space; if a parking event is recorded in the parking space, entering a leaving event judgment process on the premise of meeting a leaving updating condition; and if the parking event is not recorded in the parking place, judging the parking event.
Optionally, the off-bit update condition is: entering the leaving event judgment process when a vehicle is in the parking space and the time length from the last updating interval exceeds a threshold value or when no vehicle is in the parking space and a parking event is recorded; and if the condition is not met, returning to judge the subsequent target vehicle.
Optionally, when the target vehicle and the related information in the parking space and the related information of the empty parking space are processed, if the target vehicle is blocked, the subsequent video frame is waited for and then the judgment is performed.
Optionally, the target vehicle information, the vehicle entering and leaving event, the parking space information and the corresponding video frame are collected and sorted to generate order information, the parking space state is updated, the related images are saved in a reserved mode, and the order information and the parking space state are sent to the user.
The embodiment of the invention provides a parking space management device, which comprises:
the acquisition module is used for acquiring a video frame shot by the camera equipment, and acquiring scene information by identifying vehicles and pedestrians in the video frame to judge whether a target is blocked or not;
the tracking identification module is used for tracking the target vehicle in the scene information and identifying vehicle characteristic information;
the detection processing module is used for detecting the entering and leaving events and processing parking space information;
and the sending module is used for sending the current parking space state information and the order information to the vehicle owner client side in a preset range.
Optionally, the detection processing module includes:
the parking event judging unit is used for judging a parking event of a target vehicle in a parking space;
the off-position event judging unit is used for judging an off-position event of a target vehicle in a parking space;
and the empty parking space processing unit is used for processing the leaving event and parking space information of the empty parking space.
The embodiment of the invention provides computer equipment which comprises a memory, a processor and a computer program which is stored in the memory and can run on the processor, and is characterized in that the parking space management method is realized when the processor executes the computer program.
The embodiment of the invention provides a computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, the parking space management method is realized.
The invention provides a parking space management method, a parking space management device, computer equipment and a storage medium.A video frame shot by camera equipment is obtained, an algorithm module identifies vehicles and pedestrians in the video frame, and scene information is obtained; then, tracking the target vehicle in the scene information, and identifying vehicle characteristic information to form target vehicle information; then, combining the target vehicle information and the parking space information, and processing the target vehicle and related information in the parking space, wherein the processing comprises detecting a parking event, detecting a leaving event and updating the parking space information; and finally, processing the related information of the empty parking space by combining the parking space information and the scene information, wherein the related information comprises detecting an off-position event and updating the parking space information.
Compared with the existing parking space management system, the parking space management system can judge whether the target vehicle in the parking space is shielded by other vehicles or not through the acquired scene information, so that the parking space management system can manage the parking space for small vehicles. The small-sized vehicles comprise vehicles with strong mobility and small bodies, such as battery cars, bicycles, motorcycles and the like. Meanwhile, a mode of firstly processing the target in the parking space and then processing an empty parking space is adopted in the process, the in-place event is effectively grabbed, and the list leakage rate is reduced. Therefore, the intelligent monitoring of the parking spaces of the small vehicles can be realized, the parking spaces of the roads are effectively managed, the human resources are saved, and the single leakage rate is reduced.
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 schematic diagram of an application environment of a parking space management method according to an embodiment of the present invention;
FIG. 2 is a flowchart of a parking space management method according to an embodiment of the present invention;
FIG. 3 is a flowchart illustrating a process for processing a target vehicle and related information in a parking space according to an embodiment of the present invention;
FIG. 4 is a flow chart of an off-location event determination according to an embodiment of the present invention;
fig. 5 is a flow chart illustrating a docking event determination according to an embodiment of the present invention;
fig. 6 is a flowchart of processing information related to empty slots in an embodiment of the present invention;
FIG. 7 is a schematic block diagram of a parking space management device according to an embodiment of the present invention;
FIG. 8 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 space management method provided by the application can be applied to the application environment shown in fig. 1, wherein the camera device has data receiving and sending functions, and can exchange data with the server through a network. The camera equipment is wide-view camera equipment, and the installation selective point principle is equipped all parking stalls that can observe required control for making a video recording to can catch the license plate that can discern. The computer device may be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices. 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 space management method is provided, in which a video frame is used as a processing object, and each step is a method for processing the video frame. The target vehicle, described below, refers to a small vehicle within a video frame. The method is illustrated by taking the server applied in fig. 1 as an example, and comprises the following steps:
and S10, acquiring a video frame shot by the camera equipment, and identifying vehicles and pedestrians in the video frame by the algorithm module to acquire scene information.
In one embodiment provided by the invention, the camera device is a gun type camera and is fixedly installed at a high position, and the shooting range of the camera covers all parking spaces to be monitored. In the embodiment of the invention, the camera acquires an image video of a scene in real time, transmits a frame of image to the server for subsequent algorithm processing, and continuously transmits the next frame to the server in real time after the frame is processed.
In the embodiment of the invention, the algorithm module is a multi-classification detection model which is trained and reconstructed by using the existing deep learning network technology. In the embodiment of the invention, the scene information comprises the coordinates and the types of the detection frames of the small-sized vehicles, the automobiles and the pedestrians. The detection frame of the small-sized vehicle comprises a whole vehicle and a vehicle head and vehicle tail detection frame. The detection frame of the head and the tail of the small-sized vehicle is a main focus target of a follow-up algorithm and is used for judging whether a key point of a target vehicle falls into a parking space or not and matching the target vehicle with the parking space.
In the embodiment of the invention, the scene information is also used for judging whether the target vehicle or the parking space in the parking space is shielded or not. The conditions for judging the shielding include whether the position relations of the detection frames of other traffic participants and the parking spaces detected by the current frame coincide, whether the number of target vehicles in the parking spaces detected between the front frame and the rear frame is sharply reduced, whether the conditions of higher overlapping degree with the current parking spaces exist in the whole detection frame of the current frame battery car, and whether the parking spaces are shielded by other targets or not by judging whether the vehicle head frame and the vehicle tail frame are possibly shielded but can detect the target vehicles outside the parking spaces in the whole car and the current frame and the relations of the detection frames of the other traffic participants and the parking spaces. The above conditions may be applied alternatively or in combination according to different application scenarios, and the embodiment of the present invention is not particularly limited.
Step S20, tracking the target vehicle in the scene information, and identifying vehicle characteristic information;
before the vehicle characteristic information is recognized, it is first determined whether or not the specific vehicle information is necessary to be recognized.
In the embodiment of the present invention, the condition for determining whether to identify the specific vehicle information is that whether the server stores the feature information of the target vehicle and whether the current frame has a condition that the target feature is clearly identifiable. And if the characteristic information of the target vehicle does not exist in the server and the current frame has the condition that the target characteristics are clear and recognizable, identifying the characteristic information of the target vehicle. If the current frame does not satisfy the above condition, waiting for the subsequent video frame to be identified, and directly entering the subsequent flow, i.e. step S30.
If the vehicle characteristic information needs to be identified, after the vehicle characteristic information is identified, detecting the entering and leaving events (step S30 and step S40), and generating target vehicle information; if the identification is not needed, the detection of the in-out-of-position event is directly carried out (step S30 and step S40), and the identification is carried out when the condition in the subsequent video frame is ready.
In the embodiment of the present invention, an algorithm for tracking a target vehicle is disclosed in an invention patent with a publication number of CN110533693A filed by the applicant. And a tracking module consisting of a tracking algorithm is used for numbering the target vehicles according to the information such as the motion tracks of the target vehicles so as to realize the frame-crossing continuous marking of the same target vehicles.
In the embodiment of the present invention, the target vehicle information includes information for distinguishing a specific target vehicle, such as the target vehicle characteristic information and the number of the target vehicle during tracking.
The vehicle characteristic information is the characteristic information or the combination of the characteristic information which can distinguish a specific vehicle, such as license plate number, vehicle body characteristic, tracking number and the like. In the embodiment of the invention, the characteristic information is a license plate number, the license plate recognition algorithm is the prior art, and the invention patent with the publication number of CN107092912A, which is applied by the applicant, discloses.
And step S30, combining the target vehicle information and the parking space information, and processing the target vehicle and the related information in the parking space.
The parking space information comprises the occupation state (including vacant positions and occupation) of the current parking space, the parking position events recorded in the parking space and the binding information of the target vehicle and the parking space. The processing of the targets and the related information in the parking space comprises detecting a parking event, detecting a leaving event and updating parking space information.
As shown in fig. 3, in an embodiment provided by the present invention, step S30 processes a target vehicle and related information in a parking space, and includes:
step S301, whether a parking event is recorded in the parking space is judged.
And the parking event recorded in the parking space belongs to the sub item of the parking space information and is derived from the judgment result of the previous video frame.
If a parking event is recorded in the parking space, two situations exist in the vehicle parked in the current parking space: the vehicle is parking, or the original vehicle has left the parking place but not recorded, and the parking place is replaced by the newly parked vehicle. At this time, the process proceeds to step S302.
If the parked vehicle is not recorded in the parking space but is parked in the parking space, the parking event is judged (the specific flow is shown in fig. 5).
Step S302, judge whether meet the update condition of off-position.
The off-position updating conditions comprise whether the parking space information changes or not, the off-position updating period is timed, whether the situation that the current concerned target vehicle information in the parking space is not matched with the target vehicle information in the parking space recorded by the system exists in the previous video frame or not, and whether the parking space is detected or the target is shielded or not in the previous video frame.
In an embodiment provided by the invention, if a vehicle is in a parking space and the occupation state of each parking space in the current frame image is not changed, the off-position updating is performed after the off-position updating period reaches a threshold value. In one embodiment provided by the invention, the off-position updating period is 5 minutes, and the off-position updating period can be prolonged or shortened according to the actual monitored parking space flow condition.
In an embodiment provided by the present invention, if it is detected in the previous video frame that the information of the target vehicle in the parking space concerned currently is not matched with the information of the target vehicle in the parking space recorded by the system, or it is detected in the previous video frame that the parking space or the target is blocked but not processed, or it is satisfied that there is no vehicle in the parking space but a parking event is recorded, the departure event is determined (see fig. 4 for specific process)
If the off-position updating condition is not met, executing step S303, and returning to the judgment of the target vehicle in the subsequent parking space.
And judging an off-position event.
In an embodiment provided by the present invention, the off-position event determination process is shown in fig. 4:
firstly, matching the information of the target vehicle in the parking space with the information of the target vehicle in the parking space recorded by a server, if the matching judgment is consistent, the target vehicle in the parking space does not leave, and updating the data of the time, the picture, the information of the target vehicle and the like of the current frame into the information of the parking space to be used as the evidence of leaving the target vehicle in the parking space in the future;
if the matching judgment sections are inconsistent, whether a target vehicle in the parking space or the situation that the parking space is blocked exists is judged firstly. When the target vehicle exists in the parking space, although the target vehicle can be detected, the head or the tail of the target vehicle in the parking space can be shielded due to the stop of other traffic participants such as small-sized vehicles, automobiles and pedestrians outside the parking space, so that the matching is inconsistent. At this time, it is determined whether the parking space is blocked by obtaining the position relationship between the detection frame of the other traffic participant detected by the current frame and the parking space. If the shielding exists, delaying off-position, and returning to wait for subsequent frame judgment;
if the occlusion does not exist, judging whether the current frame image can find the corresponding target vehicle which is not in the parking space or judging the number of times of inconsistent matching. If the current frame image can find a corresponding target vehicle (driving away) which is not in the parking space, or the number of times of the inconsistent exceeding accumulated matching is judged, the corresponding target vehicle is judged to be out of position, the vehicle in the current parking space is stopped but not registered, and an out-of-position event is recorded; if the requirement is not met, the off-position is delayed, and the judgment of the subsequent frame is returned to wait.
And judging a positioning event.
In an embodiment provided by the present invention, a process of determining a docking event is shown in fig. 5:
judging whether a bound vehicle exists in the parking space, if not, binding a target vehicle in the current parking space with the parking space, and waiting for the judgment of a subsequent frame;
and if the bound vehicle exists, judging whether the target vehicle information in the current parking space is consistent with the bound vehicle information. If the parking spaces are not consistent with the parking spaces, updating the vehicles bound by the parking spaces;
and if the information of the target vehicle in the current parking space is consistent with the bound vehicle information, judging the staying time of the target vehicle in the parking space or the number of the frames kept still. If the parking time of the target vehicle in the parking space is met or the number of frames kept still exceeds a threshold value, recording the parking event of the parking space; if the requirement is not met, continuing to wait for the judgment of the subsequent frame;
and S40, processing the related information of the empty parking space by combining the parking space information and the scene information.
In an embodiment of the present invention, the processing the information related to the empty parking space includes detecting an out-of-position event and updating the parking space information. The specific flow is shown in fig. 6.
The method comprises the steps of firstly obtaining parking space information of empty parking spaces in a current frame, and sequentially judging. If no vehicle is contained in the specific parking space of the current frame, whether a parking event is recorded in the parking space information is judged firstly. If the parking event is not recorded, judging whether a bound tracking target exists in the parking space; if yes, clearing the binding target information, and if not, directly returning to wait for subsequent frame operation;
and if the parking position event is recorded in the parking position information, entering the departure judgment.
First, whether the current frame has occlusion is judged. If the blocking exists, the parking space where the vehicle is parked is possibly identified as an empty parking space by mistake, so that the misjudgment of the leaving event is caused, and the order is ended in advance. Therefore, before processing the information about the empty space, it should first be determined whether the empty space identification is accurate, i.e. whether there is a blockage. In an embodiment provided by the present invention, the method for judging occlusion includes:
firstly, judging through the difference of the number of target vehicles in the parking space detected between two frames, if the number of the target vehicles in the parking space of the current frame is sharply reduced compared with that of the target vehicles in the parking space of the previous frame, judging that the current frame is possibly blocked by a large vehicle, directly returning, and waiting for the judgment of a subsequent frame;
and then, judging whether the current frame of the whole vehicle detection frame of the small vehicle has the condition of higher overlapping degree with the current parking space. When the position relation between the vehicle and the parking space is judged, the vehicle head and parking space detection frame is taken as a focus point, so that the situation that the vehicle head or the parking space is in place but is blocked can exist, the situation that no vehicle parks in the parking space is easily judged by mistake, and the auxiliary judgment needs to be carried out by utilizing the whole vehicle detection frame. And if the vehicle head and tail detection frame has higher overlapping degree with the current parking space, the vehicle head and tail detection frame is considered to be possibly shielded. At the moment, directly returning to wait for judging a subsequent video frame;
and finally, judging the relation between the target vehicle outside the parking space in the current frame and the detection frames of other traffic participants and the parking space, and judging whether the parking space is blocked by other targets. If the shielding relation exists, directly returning to wait for judging a subsequent video frame;
if the judgment shows that the occlusion does not exist, judging whether the original target vehicle (namely the vehicle is driving away) which is not in the parking space exists in the current frame or not, or judging whether the idle duration time of the parking space exceeds a threshold value or not. And if the original target vehicle which is not in the parking space exists or the idle time of the parking space exceeds a threshold value, recording the off-position event.
In an embodiment provided by the invention, after the judgment of the entrance and departure event, the parking space information and the corresponding video frame is completed, the target vehicle information, the vehicle entrance and departure event, the parking space information and the corresponding video frame are summarized and sorted in the server to generate order information, the parking space state is updated, and the relevant images are saved in a reserved file. It should be noted that, the order information and the parking space state may be sent to the user side, so as to provide parking space state information for the user and prompt whether the parking space is free.
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 an embodiment, a parking space management device is provided, and the parking space management device corresponds to the parking space management methods in the embodiments one to one. As shown in fig. 7, the parking space management device includes an acquisition module 10, a tracking identification module 20, and a detection processing module 30. The detailed description of each functional module is as follows:
the acquisition module 10 is used for acquiring the video frames shot by the camera equipment and identifying the vehicles and pedestrians in the video frames,
acquiring scene information for judging whether a target is shielded or not;
the tracking identification module 20 is configured to track a target vehicle in the scene information and identify vehicle characteristic information;
and the detection processing module 30 is used for detecting the entering and leaving events and processing the parking space information.
In an embodiment, the parking space management apparatus further includes a sending module 40, configured to send the current parking space state information and the order information to a client of the vehicle owner within a preset range.
In an embodiment provided by the present invention, the monitoring processing module 30 includes a parking event determining unit 301, a leaving event determining unit 302, and an empty space processing unit 303, specifically:
the parking event determining unit 301 is configured to determine a parking event of a target vehicle in a parking space, and specifically configured to:
judging whether a bound vehicle exists in the parking space, if not, binding a target vehicle in the current parking space with the parking space, and waiting for subsequent frame judgment;
and if the bound vehicle exists, judging whether the information of the target vehicle in the current parking space is consistent with the information of the bound vehicle. If the parking spaces are not consistent with the parking spaces, updating the vehicles bound by the parking spaces;
and if the information of the target vehicle in the current parking space is consistent with the bound vehicle information, judging the staying time of the target vehicle in the parking space or the number of frames kept still. If the parking time of the target vehicle in the parking space is met or the number of frames kept still exceeds a threshold value, recording the parking event of the parking space; if the requirement is not met, continuing to wait for the judgment of the subsequent frame;
the leaving event determining unit 302 is configured to determine a leaving event of a target vehicle in a parking space, and specifically configured to:
the off-position updating conditions comprise whether the parking space information changes or not, the off-position updating period is timed, whether the situation that the currently concerned target vehicle information in the parking space is not matched with the target vehicle information in the parking space recorded by the system exists in the previous video frame or not, and whether the parking space is detected or the target is shielded or not by the previous video frame.
In an embodiment provided by the invention, if the occupation state of each parking space in the current frame image is not changed, the off-position updating is carried out after the off-position updating period reaches the threshold value. In one embodiment provided by the invention, the off-position updating period is 5 minutes, and the off-position updating period can be prolonged or shortened according to the actual monitored parking space flow condition.
In an embodiment provided by the present invention, if it is detected in the previous video frame that the information of the target vehicle in the parking space currently concerned is not matched with the information of the target vehicle in the parking space recorded by the system, or if it is detected in the previous video frame that the parking space or the target is blocked but not processed, the departure event is determined, and if the departure update condition is not satisfied, the determination of the target vehicle in the subsequent parking space is returned to.
The off-position event judgment is carried out according to the following steps:
firstly, matching the information of the target vehicle in the parking space with the information of the target vehicle in the parking space recorded by a server, if the matching judgment is consistent, the target vehicle in the parking space does not leave, and updating the data of the time, the picture, the information of the target vehicle and the like of the current frame into the information of the parking space to be used as the evidence of leaving the target vehicle in the parking space in the future;
if the matching judgment sections are inconsistent, whether a target vehicle in the parking space or the situation that the parking space is blocked exists is judged firstly. When the target vehicle exists in the parking space, although the target vehicle can be detected, the head or the tail of the target vehicle in the parking space can be shielded due to the stop of other traffic participants such as small-sized vehicles, automobiles and pedestrians outside the parking space, so that the matching is inconsistent. At this time, it is determined whether the parking space is blocked by obtaining the position relationship between the detection frame of the other traffic participant detected by the current frame and the parking space. If the shielding exists, delaying off-position, and returning to wait for subsequent frame judgment;
if the occlusion does not exist, judging whether the current frame image can find the corresponding target vehicle which is not in the parking space or judging the number of times of inconsistent matching. If the current frame image can find a corresponding target vehicle (driving away) which is not in the parking space, or the inconsistent more than accumulated times of matching is judged, the corresponding target vehicle is judged to be out of position, the vehicle in the current parking space is stopped but not registered, and an out-of-position event is recorded; if the requirement is not met, the off-position is delayed, and the judgment of the subsequent frame is returned to wait.
Empty parking stall processing unit 303 for handling take place in the event and the parking stall information of leaving a position in empty parking stall, specifically be used for:
the method comprises the steps of firstly obtaining parking space information of empty parking spaces in a current frame, and sequentially judging. If no vehicle is contained in the current frame specific parking space, whether the parking space information records a parking event is judged firstly. If the parking event is not recorded, judging whether a bound tracking target exists in the parking space; if yes, clearing the binding target information, and if not, directly returning to wait for subsequent frame operation;
and if the parking position event is recorded in the parking position information, entering the departure judgment.
Firstly, whether the current frame has occlusion or not is judged. If the blocking exists, the parking space where the vehicle is parked is possibly identified as an empty parking space by mistake, so that the misjudgment of the leaving event is caused, and the order is ended in advance. Therefore, before processing the information about the empty space, it should first be determined whether the empty space identification is accurate, i.e. whether there is a blockage. In an embodiment provided by the present invention, the step of determining occlusion includes:
firstly, judging through the difference of the number of target vehicles in the parking space detected between two frames, if the number of the target vehicles in the parking space of the current frame is sharply reduced compared with that of the target vehicles in the parking space of the previous frame, judging that the current frame is possibly blocked by a large vehicle, directly returning, and waiting for the judgment of a subsequent frame;
and then, judging whether the current frame of the whole vehicle detection frame of the small vehicle has the condition of higher overlapping degree with the current parking space. When the position relation between the vehicle and the parking space is judged, the vehicle head and parking space detection frame is taken as a focus point, so that the situation that the vehicle head or the parking space is in place but is blocked can exist, the situation that no vehicle is parked in the parking space can be judged by mistake, and the auxiliary judgment needs to be carried out by utilizing the whole vehicle detection frame. If the vehicle head and vehicle tail detection frame has higher overlapping degree with the current parking space, the vehicle head and vehicle tail detection frame is considered to be possibly shielded. At the moment, directly returning to wait for judging a subsequent video frame;
and finally, judging the relation between the target vehicle outside the parking space in the current frame and the detection frames of other traffic participants and the parking space, and judging whether the parking space is blocked by other targets. If the shielding relation exists, directly returning to wait for judging a subsequent video frame;
if the occlusion does not exist after the judgment, whether the original target vehicle which is not in the parking space (namely the vehicle is driving away) exists in the current frame or not is judged, or whether the idle duration time exceeds the threshold value is judged by the parking space. And if the original target vehicle which is not in the parking space exists or the idle time of the parking space exceeds a threshold value, recording the off-position event.
For specific limitations of the parking space management device, reference may be made to the above limitations of the parking space management method, which is not described herein again. All modules in the parking space management device can be completely or partially realized through 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, the internal structure of which may be as shown in fig. 7. 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 space 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 a video frame shot by the camera equipment, and identifying vehicles and pedestrians in the video frame by the algorithm module to acquire scene information;
tracking the target vehicle in the scene information, and identifying vehicle characteristic information;
combining the target vehicle information and the parking space information, and processing the target vehicle and related information in the parking space, wherein the processing comprises detecting a parking event, detecting a leaving event and updating parking space information;
and processing the related information of the empty parking space by combining the parking space information and the scene information, wherein the related information comprises detecting the leaving event and updating the parking space information.
Optionally, the target vehicle is a small vehicle such as a battery car, a bicycle, a motorcycle, and the like.
Optionally, the scene information includes coordinates of detection frames of the small vehicles, the automobiles and the pedestrians in the image, wherein the detection frames of the small vehicles include a whole automobile detection frame, a head detection frame and a tail detection frame.
Optionally, when processing the target vehicle and the related information in the parking space, firstly, judging whether a parking event is recorded in the parking space; if a parking event is recorded in the parking space, entering a leaving event judgment process on the premise of meeting a leaving updating condition; and if the parking event is not recorded in the parking place, judging the parking event.
Optionally, the off-position updating condition is: entering the leaving event judgment process when a vehicle is in the parking space and the time length from the last updating interval exceeds a threshold value or when no vehicle is in the parking space and a parking event is recorded; and if the condition is not met, returning to judge the subsequent target vehicle.
Optionally, when the target vehicle and the related information in the parking space and the related information of the empty parking space are processed, if the target vehicle is blocked, the subsequent video frame is waited for and then the judgment is performed.
Optionally, the target vehicle information, the vehicle entering and leaving event, the parking space information and the corresponding video frame are summarized and sorted to generate order information, the parking space state is updated, the relevant images are kept, and the order information and the parking space state are sent to the user.
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 a video frame shot by a camera device, and identifying traffic tools and pedestrians in the video frame by an algorithm module to acquire scene information;
tracking the target vehicle in the scene information, and identifying vehicle characteristic information;
combining the target vehicle information and the parking space information, and processing the target vehicle and related information in the parking space, wherein the processing comprises detecting a parking event, detecting a leaving event and updating the parking space information;
and processing the related information of the empty parking space by combining the parking space information and the scene information, wherein the related information comprises detecting the leaving event and updating the parking space information.
Optionally, the target vehicle is a small vehicle such as a battery car, a bicycle, a motorcycle, and the like.
Optionally, the scene information includes coordinates of detection frames of the small vehicles, the automobiles and the pedestrians in the image, wherein the detection frames of the small vehicles include a whole automobile detection frame, a head detection frame and a tail detection frame.
Optionally, when processing the target vehicle and the related information in the parking space, firstly, judging whether a parking event is recorded in the parking space; if a parking event is recorded in the parking space, entering a leaving event judgment process on the premise of meeting a leaving updating condition; and if the parking event is not recorded in the parking space, judging the parking event.
Optionally, the off-position updating condition is: entering the leaving event judgment process when a vehicle is in the parking space and the time length from the last updating interval exceeds a threshold value or when no vehicle is in the parking space and a parking event is recorded; and if the condition is not met, returning to judge the subsequent target vehicle.
Optionally, when the target vehicle and the related information in the parking space and the related information of the empty parking space are processed, if the target vehicle is blocked, the subsequent video frame is waited for and then the judgment is performed.
Optionally, the target vehicle information, the vehicle entering and leaving event, the parking space information and the corresponding video frame are summarized and sorted to generate order information, the parking space state is updated, the relevant images are kept, and the order information and the parking space state are sent to the user.
By utilizing the parking space management method, the parking space management device, the computer equipment and the storage medium, the parking space management method and the parking space management device have the following beneficial effects: the invention can judge whether the target vehicle in the parking space is shielded by other vehicles through the acquired scene information, thereby being capable of carrying out parking space management aiming at small vehicles. The small-sized vehicles comprise vehicles with strong mobility and small bodies, such as battery cars, bicycles, motorcycles and the like. Meanwhile, a mode of firstly processing the target in the parking space and then processing the empty parking space is adopted in the process, the entering-position event is effectively grabbed, and the list missing rate is reduced. Therefore, the intelligent monitoring of the parking spaces of the small vehicles can be realized, the parking spaces of the roads are effectively managed, the human resources are saved, and the single leakage rate is reduced.
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 can include non-volatile and/or volatile memory. 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 (Rambus) direct RAM (RDRAM), direct memory 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 (10)
1. The parking space management method is applied to a server, and comprises the following steps:
acquiring a video frame shot by a camera device, and identifying traffic tools and pedestrians in the video frame by an algorithm module to acquire scene information; the scene information is used for judging whether the parking space is shielded or not;
tracking the target vehicle in the scene information, and identifying vehicle characteristic information to form target vehicle information; the target vehicle is a small vehicle;
combining the target vehicle information and the parking space information, and processing the target vehicle and related information in the parking space, wherein the target vehicle and related information comprise a detection parking event, a first detection leaving event and updated parking space information; wherein the detecting a docking event comprises: if the target vehicle is determined to be consistent with the vehicle recorded in the parking space, and the target vehicle in the parking space is determined not to move greatly in a plurality of video frames, recording a parking event; the first detecting an off-position event comprises: if the matching of the information of the target vehicle in the parking space and the recorded information of the target vehicle in the parking space is inconsistent, judging whether the target vehicle in the parking space or the parking space is shielded; if the current frame image is not blocked and the corresponding target vehicle which is not in the parking space exists, recording the off-position event;
before the related information of the empty parking space is processed, the number change amplitude of the target vehicles in the parking space is determined based on the current video frame and the previous video frame; the quantity variation amplitude represents whether the parking space is blocked by a large vehicle or not;
in response to the fact that the number change amplitude is smaller than the preset change amplitude, the related information of the empty parking space is processed by combining the parking space information and the scene information, wherein the related information comprises a second detection off-position event and the parking space information is updated; wherein the second detected off-position event comprises: and if the scene information does not have a vehicle head detection frame or a vehicle tail detection frame of the small vehicle, and the overlapping degree of the vehicle detection frame of the small vehicle and the parking space in the scene information is higher than the preset overlapping degree, determining that the vehicle head detection frame or the vehicle tail detection frame is blocked, and determining that the off-position condition is not met.
2. The parking space management method according to claim 1, wherein the scene information includes coordinates of detection frames of small vehicles, automobiles and pedestrians in the image.
3. The parking space management method according to claim 1, wherein when processing the target vehicle and the related information in the parking space, first determining whether a parking event has been recorded in the parking space;
if a parking event is recorded in the parking space, entering a leaving event judgment process on the premise of meeting a leaving updating condition;
and if the parking event is not recorded in the parking space, judging the parking event.
4. The parking space management method according to claim 3, wherein the leaving update condition is:
entering the leaving event judgment process when a vehicle is in the parking space and the time length from the last updating interval exceeds a threshold value or when no vehicle is in the parking space and a parking event is recorded;
and if the condition is not met, returning to judge the subsequent target vehicle.
5. The parking space management method according to claim 1, wherein when processing the target vehicle and the related information in the parking space and processing the related information of the empty parking space, if the target vehicle is blocked, the judgment is performed after waiting for the subsequent video frame.
6. The parking space management method according to claim 1, wherein the target vehicle information, the vehicle entering and leaving event, the parking space information and the corresponding video frames are collected and sorted to generate order information, the parking space state is updated, the relevant images are saved in a reserved mode, and the order information and the parking space state are sent to a user.
7. The utility model provides a parking stall management device which characterized in that, the device includes:
the acquisition module is used for acquiring a video frame shot by the camera equipment, and acquiring scene information by identifying vehicles and pedestrians in the video frame to judge whether a target is blocked or not;
the tracking identification module is used for tracking the target vehicle in the scene information and identifying vehicle characteristic information; the target vehicle is a small vehicle;
the detection processing module is used for detecting the entering and leaving events and processing parking space information;
the sending module is used for sending the current parking space state information and the order information to the vehicle owner client side in the preset range,
wherein, the detection processing module is further used for executing:
combining the target vehicle information and the parking space information, and processing the target vehicle and related information in the parking space, wherein the target vehicle and related information comprise a detection parking event, a first detection leaving event and updated parking space information; wherein the detecting a docking event comprises: if the target vehicle is determined to be consistent with the vehicle recorded in the parking space, and the target vehicle in the parking space is determined not to move greatly in a plurality of video frames, recording a parking event; the first detecting an off-position event comprises: if the matching of the information of the target vehicle in the parking space and the recorded information of the target vehicle in the parking space is inconsistent, whether the target vehicle or the parking space in the parking space is blocked is judged; if the target vehicle is not blocked and the corresponding target vehicle which is not in the parking space exists in the current frame image, recording an off-position event;
before the relevant information of the empty parking space is processed, the number change amplitude of the target vehicles in the parking space is determined based on the current video frame and the last video frame; the quantity variation amplitude represents whether the parking space is blocked by a large vehicle or not;
in response to the fact that the number variation amplitude is smaller than the preset variation amplitude, processing related information of the empty parking space by combining the parking space information and the scene information, wherein the related information comprises a second detection off-position event and the parking space information is updated; wherein the second detected off-position event comprises: and if the scene information does not have a vehicle head detection frame or a vehicle tail detection frame of the small-sized vehicle and the overlapping degree of the vehicle detection frame of the small-sized vehicle and the parking space in the scene information is higher than a preset overlapping degree, determining that the vehicle head detection frame or the vehicle tail detection frame is shielded, and determining that the off-position condition is not met.
8. The parking space management device according to claim 7, wherein the detection processing module comprises:
the parking event judging unit is used for judging a parking event of a target vehicle in a parking space;
the off-position event judging unit is used for judging an off-position event of a target vehicle in a parking space;
and the empty parking space processing unit is used for processing the leaving event and parking space information of the empty parking space.
9. 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 method of space management according to any of claims 1 to 6 when executing the computer program.
10. A computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, implements the space management method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011204599.2A CN112382101B (en) | 2020-11-02 | 2020-11-02 | Parking space management method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011204599.2A CN112382101B (en) | 2020-11-02 | 2020-11-02 | Parking space management method and device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112382101A CN112382101A (en) | 2021-02-19 |
| CN112382101B true CN112382101B (en) | 2022-11-04 |
Family
ID=74577144
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011204599.2A Active CN112382101B (en) | 2020-11-02 | 2020-11-02 | Parking space management method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112382101B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107610499A (en) * | 2016-07-11 | 2018-01-19 | 富士通株式会社 | Detection method, detection means and the electronic equipment of parking stall state |
| CN110322681A (en) * | 2018-03-30 | 2019-10-11 | 杭州海康威视数字技术股份有限公司 | The method and apparatus for detecting parking space state |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107292277B (en) * | 2017-06-30 | 2020-08-21 | 深圳信路通智能技术有限公司 | Trackable method for roadside double-parking-space parking |
| CN110009929A (en) * | 2019-03-15 | 2019-07-12 | 北京筑梦园科技有限公司 | A kind of Vehicle berth management method, equipment and system |
| CN110930729A (en) * | 2019-11-13 | 2020-03-27 | 北京智芯原动科技有限公司 | Low-pole road side parking detection method and device based on video |
| CN111784857A (en) * | 2020-06-22 | 2020-10-16 | 浙江大华技术股份有限公司 | Parking space management method and device and computer storage medium |
| CN111862625A (en) * | 2020-07-13 | 2020-10-30 | 深圳前海华夏智信数据科技有限公司 | In-road parking video pile and parking management method |
-
2020
- 2020-11-02 CN CN202011204599.2A patent/CN112382101B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107610499A (en) * | 2016-07-11 | 2018-01-19 | 富士通株式会社 | Detection method, detection means and the electronic equipment of parking stall state |
| CN110322681A (en) * | 2018-03-30 | 2019-10-11 | 杭州海康威视数字技术股份有限公司 | The method and apparatus for detecting parking space state |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112382101A (en) | 2021-02-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112365719B (en) | Parking space 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 | |
| CN108806272B (en) | Method and device for reminding multiple motor vehicle owners of illegal parking behaviors | |
| CN112364742A (en) | Parking space management method and device, computer equipment and storage medium | |
| CN106600977A (en) | Parking violation detection method and system based on multi-feature identification | |
| CN110738150B (en) | Camera linkage snapshot method and device and computer storage medium | |
| CN109714576B (en) | Vehicle identification method, device and system based on video monitoring and server | |
| CN113055823B (en) | Method and device for managing shared bicycle based on road side parking | |
| WO2021184570A1 (en) | Method and apparatus for identifying driving behaviors of electric bicycle, and computer device | |
| CN108932849B (en) | Method and device for recording low-speed running illegal behaviors of multiple motor vehicles | |
| CN112509325A (en) | Video deep learning-based off-site illegal automatic discrimination method | |
| CN112598925A (en) | Parking management method and device, computer equipment and storage medium | |
| CN114005074B (en) | Traffic accident determination method and device and electronic equipment | |
| CN112396708B (en) | Parking management method, parking management device, computer equipment and storage medium | |
| CN112382101B (en) | Parking space management method and device, computer equipment and storage medium | |
| WO2023246720A1 (en) | Roadside parking detection method, roadside parking system, and electronic device | |
| CN105761501A (en) | Intelligent vehicle behavior detecting and snapshotting method | |
| CN115131737A (en) | Vehicle cleaning state identification method and device and electronic equipment | |
| CN111462480B (en) | Traffic image evidence verification method and device, computer equipment and storage medium | |
| CN111274931A (en) | Overtaking behavior auditing method and device, computer equipment and storage medium | |
| CN111526475A (en) | Target vehicle tracking method and device, electronic equipment and storage medium | |
| CN113689671B (en) | Urban underground space security alarm method and system | |
| CN113269011B (en) | Vehicle detection method, device, equipment and storage medium | |
| CN114566058B (en) | Management method and system for operation and maintenance monitoring data of highway | |
| CN116758468A (en) | Vehicle entrance/exit monitoring method and device, computer equipment and storage medium |
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 |