CN112396843A - Method for roadside parking detection by using vehicle detection model - Google Patents
Method for roadside parking detection by using vehicle detection model Download PDFInfo
- Publication number
- CN112396843A CN112396843A CN202011329389.6A CN202011329389A CN112396843A CN 112396843 A CN112396843 A CN 112396843A CN 202011329389 A CN202011329389 A CN 202011329389A CN 112396843 A CN112396843 A CN 112396843A
- Authority
- CN
- China
- Prior art keywords
- parking
- vehicle
- parking space
- camera
- information
- 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.)
- Withdrawn
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
- 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
- G08G1/14—Traffic control systems for road vehicles indicating individual free spaces in parking areas
- G08G1/149—Traffic control systems for road vehicles indicating individual free spaces in parking areas coupled to means for restricting the access to the parking space, e.g. authorization, access barriers, indicative lights
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Business, Economics & Management (AREA)
- Finance (AREA)
- Traffic Control Systems (AREA)
- Devices For Checking Fares Or Tickets At Control Points (AREA)
Abstract
The invention discloses a method for roadside parking detection by using a vehicle detection model, which is characterized in that an L rod is arranged on a sidewalk on one side opposite to a roadside parking space, a gun-shaped integrated camera and a light supplement lamp are arranged on the L rod, and the installation directions of the camera and the light supplement lamp face to the central area of a target parking space; dividing a target area of a camera into a road area and a parking space area, dividing each parking space area according to a field picture, and shooting the target area by using the camera; the method comprises the steps of detecting a moving object in a video stream through a camera, detecting the position of a license plate in the moving object, identifying vehicle information such as the license plate, detecting a parking space area by using a vehicle detection model, and sending the parking space information to a server. The method detects parking in/out of a vehicle in a roadside parking space through a single gun-shaped integrated camera, and meanwhile, a vehicle detection model is used for carrying out shooting supplementing on missing shooting of parking in/out.
Description
Technical Field
The invention relates to the field of parking space management, in particular to a method for detecting roadside parking on ARM embedded equipment by a vehicle detection model.
Background
Parking is a very important need in urban life, and the difficulty in parking becomes a problem which needs to be solved urgently in urban development. It is known that 20 billion cars will travel on the highway and the traffic system will be more busy by 2020. Therefore, in order to solve the problem of difficult parking, many temporary parking spaces are arranged on the roadside of a city, but the management and charging of the temporary parking spaces have many problems:
1. pure manual charging: the problems of untimely charge, fee evasion and non-handed charge of the toll collector can occur, and the toll collector is easy to have dispute with the vehicle owner and cannot handle the dispute, so that the labor cost is very high;
2. geomagnetic induction: after the vehicle is sensed by geomagnetism, the toll collector charges the vehicle, and meanwhile, the problems of fee evasion, dispute and the like exist, and the labor cost is high;
3. the method has the advantages that the installation is complex, the gun and the dome camera are required to work in a linkage mode, the switching of the gun and the dome camera requires time, the parking or the exiting of the vehicles cannot be simultaneously captured in the same time, and the recognition rate is low.
Disclosure of Invention
The invention provides a method for detecting roadside automobiles by using a vehicle detection model, aiming at the defects of the existing roadside parking management mode.
The technical scheme for realizing the purpose of the invention is as follows:
a method for roadside parking detection by using a vehicle detection model comprises the following steps:
(1) installing an L rod on a sidewalk on one side opposite to a roadside parking space, installing a gun-shaped integrated camera and a light supplement lamp on the L rod, and enabling the installation directions of the camera and the light supplement lamp to face to the central area of a target parking space; the gun-shaped integrated camera is internally provided with an embedded roadside parking processing system and is used for shooting images of a target area, identifying license plate information parked on a parking space and detecting the parking space occupation state of the target area;
(2) setting a target area of a camera, dividing the target area into a road area and a parking space area, dividing each parking space area according to a field picture, and shooting the target area by using the camera;
(3) detecting a moving object in a video stream through a camera, detecting the position of a license plate in the moving object, identifying vehicle information such as the license plate and the like, tracking the vehicle according to the vehicle information, judging the parking in and parking out of the vehicle according to the vehicle tracking information, and updating the parking in/parking out state of each parking space;
(4) detecting a parking space area by using a vehicle detection model built in the embedded roadside parking processing system, and simultaneously comparing the parking space area with the existing parking space state; when the detected parking space state is different from the existing parking space state, carrying out complementary shooting parking or parking out through a vehicle detection model;
(5) the camera sends the parking/exiting state of the parking space and the parking/exiting information of the vehicle to the server, and the server charges the fee in a timing mode according to the parking/exiting information of the vehicle.
The embedded roadside parking processing system is formed by mutually connecting a mobile detection module, a license plate recognition module, a video tracking module and a vehicle detection model, wherein:
the mobile detection module is used for detecting a moving object in a target area in the video stream and transmitting the position information of the moving object to the license plate identification module;
the license plate recognition module is used for detecting the position of a license plate from the position information transmitted by the movement detection module, recognizing vehicle information such as the license plate number and the like, and transmitting the vehicle information to the video tracking module;
and the video tracking module is used for tracking the position of the vehicle, analyzing the behavior and the track of the vehicle according to the obtained vehicle position information, and judging the parking/parking of the vehicle.
And the vehicle detection model is used for detecting the vehicle information state on the parking space at regular time, detecting the vehicle information state once every 5 seconds, and entering into/exiting from the parking supplemental photographing action when the detected state is different from the original parking space state.
The vehicle detection model is a single-step convolutional neural network.
The invention has the beneficial effects that: the system has the advantages that the single gun-shaped camera is used for detecting vehicle parking/parking out of the roadside parking space, manual management is not needed, the cost is saved, the parking/parking out detection rate is high, the vehicle detection model is added on the basis of the original roadside parking detection system, secondary supplementary shooting can be carried out on the parked/parked vehicle, the parking/parking out missing shooting caused by shielding and other reasons is effectively avoided, the parking/parking out detection rate is increased, the vehicle detection model runs on an ARM embedded device, a GPU is not needed, and the influence on the identification frame rate of the camera is small.
Drawings
FIG. 1 is a schematic view of an embodiment of a gun-type integrated camera for detecting roadside berthing;
FIG. 2 is a flowchart illustrating a procedure for determining docking/undocking according to an embodiment of the present invention;
FIG. 3 is a flowchart illustrating the operation of a vehicle detection model according to an embodiment of the present invention.
Detailed Description
The invention is further illustrated by the following figures and examples, but is not limited to the content of the invention.
Example (b):
a method for roadside parking detection by using a vehicle detection model comprises the following steps:
(1) an L rod is arranged on a sidewalk on one side opposite to a roadside parking space, a gun-shaped integrated camera and a light supplement lamp are arranged on the L rod, and the installation directions of the camera and the light supplement lamp face to the central area of a target parking space (as shown in figure 1);
(2) setting a target area of a camera, dividing the target area into a road area and a parking space area, dividing each parking space area according to a field picture, shooting the target area by using the camera of a built-in ARM embedded system, and analyzing vehicle parking-in/parking-out information in the target area; the embedded processing system is divided into a mobile detection module, a license plate recognition module, a video tracking module and a vehicle detection model;
(3) the mobile detection module detects a moving object in a target area in the video stream and transmits the position information of the moving object to the license plate identification module;
(4) and the license plate recognition module detects the position of the license plate from the position transmitted by the movement detection module, recognizes the vehicle information such as the license plate number and the like, and transmits the vehicle information to the video tracking module.
(5) The video tracking module is used for establishing vehicle tracking according to information such as license plates and the like, judging that the vehicle is parked when the tracked vehicle moves from the outside of the parking space area to the inside of the parking space area and stops moving, and marking the parking space as a parking state, wherein the parking space area corresponding to the last position of the vehicle is a parked parking space number;
(6) for a parking space in a parking state, when a license plate number of the parking space is identified in a road area, judging that a vehicle in the parking space is parked out, and marking the parking space as a parking out state (as shown in fig. 2);
(7) and the vehicle detection model is used for detecting the parking space area every 5 seconds and comparing the parking space area with the existing parking space state. If the parking space is in the parking state, the parking space state is marked as 1, and if the parking space is in the parking state, the parking space state is marked as 0, and similarly, when the vehicle detection model detects that a vehicle is in the parking space, the detection state is marked as 1, and the parking space is not in the parking space and is marked as 0. If the vehicle is detected to stop beside the parking space, the parking space is shielded, and the calculation of the parking space is skipped;
when the parking space state is 0, the detection state of the vehicle detection model is 1, and the number of times of continuously detecting the state is greater than a set threshold value, the parking space is indicated that a vehicle is parked in but a camera is not shot, the server is informed to carry out shooting and parking again, and the parking space state is set to be 1;
when the parking space state is 1, the detection state is 0, and the number of times of continuously detecting the state is greater than the set threshold value, it indicates that the vehicle is parked out of the parking space but the camera is not shot, at this time, a message of parking out of the vehicle in the parking space is reissued to the server, and the parking space state is set to 0 (as shown in fig. 3);
(8) the camera sends the parking/exiting state of the parking space and the parking/exiting information of the vehicle in the parking space to the server, and the server performs timing charging according to the parking/exiting information of the vehicle.
Claims (3)
1. A method for roadside parking detection by using a vehicle detection model is characterized by comprising the following steps: the method comprises the following steps:
(1) installing an L rod on a sidewalk on one side opposite to a roadside parking space, installing a gun-shaped integrated camera and a light supplement lamp on the L rod, and enabling the installation directions of the camera and the light supplement lamp to face to the central area of a target parking space; the gun-shaped integrated camera is internally provided with an embedded roadside parking processing system and is used for shooting images of a target area, identifying license plate information parked on a parking space and detecting the parking space occupation state of the target area;
(2) setting a target area of a camera, dividing the target area into a road area and a parking space area, dividing each parking space area according to a field picture, and shooting the target area by using the camera;
(3) detecting a moving object in a video stream through a camera, detecting the position of a license plate in the moving object, identifying vehicle information such as the license plate and the like, tracking the vehicle according to the vehicle information, judging the parking in and parking out of the vehicle according to the vehicle tracking information, and updating the parking in/parking out state of each parking space;
(4) detecting a parking space area by using a vehicle detection model built in the embedded roadside parking processing system, and simultaneously comparing the parking space area with the existing parking space state; when the detected parking space state is different from the existing parking space state, carrying out complementary shooting parking or parking out through a vehicle detection model;
(5) the camera sends the parking/exiting state of the parking space and the parking/exiting information of the vehicle to the server, and the server charges the fee in a timing mode according to the parking/exiting information of the vehicle.
2. The method for roadside parking detection using a vehicle detection model as claimed in claim 1, wherein: the embedded roadside parking processing system is formed by mutually connecting a mobile detection module, a license plate recognition module, a video tracking module and a vehicle detection model, wherein:
the mobile detection module is used for detecting a moving object in a target area in the video stream and transmitting the position information of the moving object to the license plate identification module;
the license plate recognition module is used for detecting the position of a license plate from the position information transmitted by the movement detection module, recognizing vehicle information such as the license plate number and the like, and transmitting the vehicle information to the video tracking module;
the video tracking module is used for tracking the position of the vehicle, analyzing the behavior and the track of the vehicle according to the obtained vehicle position information, and judging the parking in/out of the vehicle;
and the vehicle detection model is used for detecting the vehicle information state on the parking space at regular time, detecting the vehicle information state once every 5 seconds, and entering into/exiting from the parking supplemental photographing action when the detected state is different from the original parking space state.
3. The method for roadside parking detection using a vehicle detection model as claimed in claim 1, the vehicle detection model being a single step convolutional neural network.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011329389.6A CN112396843A (en) | 2020-11-24 | 2020-11-24 | Method for roadside parking detection by using vehicle detection model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011329389.6A CN112396843A (en) | 2020-11-24 | 2020-11-24 | Method for roadside parking detection by using vehicle detection model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112396843A true CN112396843A (en) | 2021-02-23 |
Family
ID=74607697
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011329389.6A Withdrawn CN112396843A (en) | 2020-11-24 | 2020-11-24 | Method for roadside parking detection by using vehicle detection model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112396843A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113205689A (en) * | 2021-04-09 | 2021-08-03 | 超级视线科技有限公司 | Multi-dimension-based roadside parking admission event judgment method and system |
| CN113205690A (en) * | 2021-04-09 | 2021-08-03 | 超级视线科技有限公司 | Roadside parking departure event judgment method and system based on multiple dimensions |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170032199A1 (en) * | 2015-07-31 | 2017-02-02 | Fujitsu Limited | Video data analyzing method and apparatus and parking lot monitoring system |
| KR101756849B1 (en) * | 2016-11-01 | 2017-07-12 | 주식회사한맥아이피에스 | Parking control and management system for on-street parking lot |
| US20170328731A1 (en) * | 2016-05-11 | 2017-11-16 | GE Lighting Solutions, LLC | System and stereoscopic range determination method for a roadway lighting system |
| CN107945521A (en) * | 2017-11-20 | 2018-04-20 | 青岛比特信息技术有限公司 | A kind of rifle ball linkage trackside is parked detecting system and method |
| CN107945566A (en) * | 2017-11-17 | 2018-04-20 | 张慧 | Curb parking management system and method based on multiple target tracking and deep learning |
| CN108765973A (en) * | 2018-06-01 | 2018-11-06 | 智慧互通科技有限公司 | A kind of Roadside Parking management system based on the complementation of offside visual angle |
| KR20180124477A (en) * | 2017-05-12 | 2018-11-21 | 주식회사 대영아이오티 | System and method for managing parking |
| CN109993979A (en) * | 2019-03-14 | 2019-07-09 | 桂林金铱星科技发展有限公司 | A kind of roadside that installing gun shaped video camera using side dress mode is parked detection method |
| CN209560722U (en) * | 2019-04-22 | 2019-10-29 | 桂林金铱星科技发展有限公司 | A kind of roadside based on polyphaser linkage is parked detection system |
| CN110930764A (en) * | 2019-12-12 | 2020-03-27 | 桂林金铱星科技发展有限公司 | Roadside parking detection method based on inspection method |
-
2020
- 2020-11-24 CN CN202011329389.6A patent/CN112396843A/en not_active Withdrawn
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170032199A1 (en) * | 2015-07-31 | 2017-02-02 | Fujitsu Limited | Video data analyzing method and apparatus and parking lot monitoring system |
| US20170328731A1 (en) * | 2016-05-11 | 2017-11-16 | GE Lighting Solutions, LLC | System and stereoscopic range determination method for a roadway lighting system |
| KR101756849B1 (en) * | 2016-11-01 | 2017-07-12 | 주식회사한맥아이피에스 | Parking control and management system for on-street parking lot |
| KR20180124477A (en) * | 2017-05-12 | 2018-11-21 | 주식회사 대영아이오티 | System and method for managing parking |
| CN107945566A (en) * | 2017-11-17 | 2018-04-20 | 张慧 | Curb parking management system and method based on multiple target tracking and deep learning |
| CN107945521A (en) * | 2017-11-20 | 2018-04-20 | 青岛比特信息技术有限公司 | A kind of rifle ball linkage trackside is parked detecting system and method |
| CN108765973A (en) * | 2018-06-01 | 2018-11-06 | 智慧互通科技有限公司 | A kind of Roadside Parking management system based on the complementation of offside visual angle |
| CN109993979A (en) * | 2019-03-14 | 2019-07-09 | 桂林金铱星科技发展有限公司 | A kind of roadside that installing gun shaped video camera using side dress mode is parked detection method |
| CN209560722U (en) * | 2019-04-22 | 2019-10-29 | 桂林金铱星科技发展有限公司 | A kind of roadside based on polyphaser linkage is parked detection system |
| CN110930764A (en) * | 2019-12-12 | 2020-03-27 | 桂林金铱星科技发展有限公司 | Roadside parking detection method based on inspection method |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113205689A (en) * | 2021-04-09 | 2021-08-03 | 超级视线科技有限公司 | Multi-dimension-based roadside parking admission event judgment method and system |
| CN113205690A (en) * | 2021-04-09 | 2021-08-03 | 超级视线科技有限公司 | Roadside parking departure event judgment method and system based on multiple dimensions |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR100768820B1 (en) | In-car type illegal vehicles detection system while driving and method of using the same | |
| KR101671428B1 (en) | Intelligent Monitoring System For Violation Vehicles in crossroads | |
| CN108877269B (en) | Intersection vehicle state detection and V2X broadcasting method | |
| CN104574540A (en) | Electronic toll collection system and method | |
| CN102332209A (en) | Automobile violation video monitoring method | |
| CN111325858B (en) | Method for realizing automatic charging management aiming at roadside temporary parking space | |
| CN104574998A (en) | Vehicle-mounted type device and method for detecting violations | |
| CN105678852A (en) | Multi-lane free flow (MLFF) electronic toll collection (ETC) lane system and license plate identification method thereof | |
| CN112396843A (en) | Method for roadside parking detection by using vehicle detection model | |
| CN110930764A (en) | Roadside parking detection method based on inspection method | |
| CN107123270A (en) | A kind of intelligent managing and control system in building site for slag-soil truck | |
| CN105809752A (en) | ETC system integrated with infrared camera function, and vehicle identification and location method | |
| CN110766978A (en) | Unmanned aerial vehicle-based roadside parking management method and system and storage medium | |
| CN109544940A (en) | Bus special lane road occupying capturing system and its grasp shoot method based on trinocular vision | |
| CN112382104A (en) | Roadside parking management method based on vehicle track analysis | |
| CN112364742A (en) | Parking space management method and device, computer equipment and storage medium | |
| CN113593246B (en) | Method for identifying and binding license plate and parking space of vehicle | |
| CN114419925B (en) | Vehicle-road cooperative collision-prevention early warning system and method | |
| CN111260953A (en) | In-road parking management method, device and system | |
| CN113643547B (en) | Method for identifying and binding license plate and parking space of vehicle | |
| CN105761501A (en) | Intelligent vehicle behavior detecting and snapshotting method | |
| CN113593247B (en) | Parking management system | |
| CN113345118B (en) | Parking charge management method, system and storage medium | |
| CN210629675U (en) | Night meeting illegal use high beam automatic recording equipment | |
| KR200415231Y1 (en) | In-car type illegal vehicles detection system while driving |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210223 |
|
| WW01 | Invention patent application withdrawn after publication |