CN111666784A - Intelligent parking device based on visual image algorithm - Google Patents

Intelligent parking device based on visual image algorithm Download PDF

Info

Publication number
CN111666784A
CN111666784A CN201910167213.6A CN201910167213A CN111666784A CN 111666784 A CN111666784 A CN 111666784A CN 201910167213 A CN201910167213 A CN 201910167213A CN 111666784 A CN111666784 A CN 111666784A
Authority
CN
China
Prior art keywords
vehicle
information
module
visual image
camera
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.)
Pending
Application number
CN201910167213.6A
Other languages
Chinese (zh)
Inventor
余国勤
唐琎
薛韬略
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Central South University
Original Assignee
Central South University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Central South University filed Critical Central South University
Priority to CN201910167213.6A priority Critical patent/CN111666784A/en
Publication of CN111666784A publication Critical patent/CN111666784A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16Human faces, e.g. facial parts, sketches or expressions
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00Scenes; Scene-specific elements
    • G06V20/50Context or environment of the image
    • G06V20/56Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00Scenes; Scene-specific elements
    • G06V20/50Context or environment of the image
    • G06V20/56Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
    • G06V20/58Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
    • G06V20/586Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of parking space

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Human Computer Interaction (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention discloses an intelligent parking device based on a visual image algorithm, which belongs to the technical field of intelligent parking and comprises a processor, a database for storing vehicle information of a vehicle owner, a dynamic video analysis system, an identification system, a path planning module, a timing module and a mobile client, wherein the dynamic video analysis system comprises a visual sensor, an all-directional camera and a video acquisition module for capturing video through the camera, the identification system comprises a license plate identification module, a face identification module and a radio frequency card identification module, the processor is respectively connected with the database, the dynamic video analysis system and the identification system path planning system timing module, and the database is respectively connected with the dynamic video analysis system, the identification system and the path planning module. The invention identifies the face and the license plate through a visual image algorithm, and simultaneously uses a route planning and calculation rule to plan the driving path, and displays the relevant information to the vehicle owner through the mobile client.

Description

Intelligent parking device based on visual image algorithm
Technical Field
The invention relates to a parking device, in particular to an intelligent parking device based on a visual image algorithm, and belongs to the technical field of intelligent parking.
Background
By the end of 2018, the number of motor vehicles in the country reaches 3.9 hundred million, wherein 2.94 hundred million automobiles are kept; 4.2 million people are motor vehicle drivers, with over 3.8 million car drivers. People have increasingly vigorous rigidity requirements on automobiles, and the explosive growth of the number of automobiles has higher requirements on the bearing capacity of transportation, so that the related problems of parking and parking lots are brought, and in order to comply with social development, the market is continuously enlarged to upgrade and reform an intelligent transportation system, wherein the upgrading and reforming technology comprises the wide application of a license plate recognition technology, a face recognition technology and a route planning technology.
The popularization of the internet of things, big data and cloud computer technology, intelligent building and smart city construction in China can be greatly developed. The information benefits people, the intelligent traffic and the safe communities all come out like spring bamboo shoots after rain, are blossoming and prosperous, and promote the depth and the breadth of urban modernization. The internet of vehicles is becoming a reality from blueprints, and as an essential part of the internet of vehicles, intelligent parking lots will highlight their higher value.
When a vehicle enters a parking lot, a vehicle owner cannot know the number and the positions of empty parking spaces in the parking lot, often spends a lot of time finding the parking spaces to park, sometimes the vehicle owner forgets where the vehicle is parked, spends a lot of time finding the parking spaces, and spends time paying money when leaving the parking lot.
At present, a set of intelligent parking device is needed, and manual intervention is not needed from the time when a car arrives at a parking lot, the car is found, the car is parked in the parking lot, the car is found, and the car leaves the parking lot, so that automatic parking is realized.
Disclosure of Invention
The invention mainly aims to provide an intelligent parking device based on a visual image algorithm, which is used for identifying a human face and a license plate through the visual image algorithm, simultaneously planning a driving path by adopting different route planning rules, and displaying relevant information to a vehicle owner through a mobile client.
The purpose of the invention can be achieved by adopting the following technical scheme:
the utility model provides an intelligence parking equipment based on visual image algorithm, includes treater, storage owner vehicle information's database, dynamic video analytic system, identification system, route planning module, timing module and mobile client, dynamic video analytic system includes vision sensor, all-round camera and carries out the video acquisition module that the video was caught through the camera, identification system includes license plate recognition module, face identification module and radio frequency card identification module, the treater respectively with database, dynamic video analytic system, identification system route planning system timing module link to each other, the database respectively with dynamic video analytic system, identification system, route planning module link to each other.
In any of the above schemes, preferably, the database stores owner information, vehicle information, and a historical parking record, the owner information includes a vehicle owner phone number, a face image, and a parking fee, and the vehicle information includes a license plate number and a vehicle type.
In any of the above schemes, preferably, the video capture module records dynamic information of the vehicle by using a multi-camera information fusion technology and a video tracking technology.
In any of the above schemes, preferably, the multi-camera information fusion technique performs video fusion on a plurality of videos by performing motion segmentation, object classification, and behavior understanding by using a plurality of cameras.
In any of the above schemes, preferably, the video tracking technology tracks the vehicle motion track by using kalman filtering and a condensation algorithm based on a multi-camera information fusion technology.
In any of the above schemes, preferably, the route planning module adopts dijk-stra algorithm, including the number of road segments participating in calculation, the reading efficiency of topology data and the sorting efficiency of the temporary table, and provides a plurality of routes for the vehicle owner to select by taking route rationality, time consumption, space consumption and hardware cost as weights.
In any of the above schemes, preferably, the parking lot entrance is provided with a license plate recognition camera and a face recognition camera, and each parking space is provided with a camera.
In any of the above schemes, preferably, the mobile client includes an in-vehicle system, a mobile phone APP and an applet, and is configured to provide the information of the vacant parking spaces, the route information and the parking time cost information for the vehicle owner.
The invention has the beneficial technical effects that: according to the intelligent parking device based on the visual image algorithm, the intelligent parking device based on the visual image algorithm is combined with the automatic license plate recognition system and the face recognition technology, a vehicle owner and a vehicle can be connected, the vehicle stealing behavior is prevented, the vehicle running route can be analyzed by the dynamic video analysis system, the nearest parking space is provided, the vehicle owner can park rapidly, and a large amount of time is saved.
Drawings
FIG. 1 is a flow diagram of a multi-camera video fusion technique in accordance with a preferred embodiment of the intelligent parking apparatus based on visual image algorithm of the present invention;
fig. 2 is a circuit connection block diagram of a preferred embodiment of the intelligent parking apparatus based on the visual image algorithm according to the present invention.
Detailed Description
In order to make the technical solutions of the present invention more clear and definite for those skilled in the art, the present invention is further described in detail below with reference to the examples and the accompanying drawings, but the embodiments of the present invention are not limited thereto.
As shown in fig. 1, the intelligent parking apparatus based on the visual image algorithm provided in this embodiment includes a processor, a database storing vehicle information of a vehicle owner, a dynamic video analysis system, an identification system, a path planning module, a timing module, and a mobile client, where the dynamic video analysis system includes a visual sensor, an omnidirectional camera, and a video acquisition module capturing video through the camera, the identification system includes a license plate identification module, a face identification module, and a radio frequency card identification module, the processor is respectively connected to the database, the dynamic video analysis system, and the identification system path planning system timing module, and the database is respectively connected to the dynamic video analysis system, the identification system, and the path planning module.
Furthermore, in the present embodiment, an automatic license plate recognition system is preferred, which can capture images of all in-and-out motor vehicles and support multiple detection modes such as ground coil detection and video detection. The backup among various detection modes is supported, when the local induction coil detection equipment breaks down, the system can be automatically converted into a video detection mode, and the probability of missed shooting is greatly reduced.
The license plate automatic identification system is matched, on the basis of a high-definition all-directional camera and a vision sensor, the lighting technology and the control technology of a patent are supplemented, the face identification technology is adopted, clear face image information of a driver can be obtained in various time periods, various environment light (under the conditions of strong direct light and strong backlight) and various weather conditions, when vehicle information is captured, the actual driver of the current vehicle can be recorded, and the identity verification of a manager is facilitated.
Further, in this embodiment, the database stores owner information, vehicle information, and historical parking records, the owner information includes a vehicle owner phone number, a face image, and parking fees, the vehicle information includes a license plate number and a vehicle type, and the implementation of artificial intelligence must be combined with big data, that is, must have a sufficient sample size. In the intelligent parking system, fuzzy matching is used as fuzzy of character strings and mainly helps calculation accuracy.
If a vehicle parks for many times at different time, enough sample amount can be left on the background by the license plate number and the vehicle owner information, the intelligent parking system is matched with the database through a visual image algorithm, the matching result is removed by using visual artificial intelligence, and the accuracy is improved similarly to gene detection.
Further, in this embodiment, the video capture module records the dynamic information of the vehicle by using a multi-camera information fusion technology and a video tracking technology, and a plurality of cameras are installed at each intersection turning position and each parking space position, so that the vehicle cannot be shot at a dead angle.
Further, in the present embodiment, as shown in fig. 1, the multi-camera information fusion technique performs motion segmentation, object classification, and behavior understanding through a plurality of cameras, and performs video fusion on a plurality of videos.
Further, in the embodiment, the video tracking technology adopts kalman filtering and an agglomeration algorithm, and tracks the vehicle motion track based on a multi-camera information fusion technology.
Further, in this embodiment, the route planning module uses dijk-stra algorithm, which includes the number of road segments participating in calculation, the reading efficiency of topology data, and the sorting efficiency of temporary tables, and provides multiple routes for the vehicle owner to select according to the weight of route reasonableness, time consumption, space consumption, and hardware cost, and route planning usually does not use one algorithm, but a set of mutually combined and supported strategies and algorithms, such as M2M, abstraction layer, partition, and the like, may be effectively combined together.
The use of the thread can improve the planning efficiency of a single route, the thread can be used in a partitioning and layering planning strategy and can also be used in a bidirectional planning algorithm, the bidirectional planning has certain requirements on topology, namely a necessary reverse adjacency list needs to be established, and the basic route planning condition is generally the shortest distance and the shortest time.
Further, in this embodiment, the parking lot entrance is equipped with license plate recognition camera and face recognition camera, all is equipped with the camera on every parking stall, can discern which parking stall the vehicle is berthhed at.
Further, in this embodiment, the mobile client includes a vehicle-mounted system, a mobile phone APP and a small program, and is used for providing the vehicle owner with vacant parking space information, route information and parking time fee information.
In this embodiment, the intelligent parking process based on the visual image algorithm is as follows:
the method comprises the following steps that a vehicle owner drives a vehicle to an entrance of a parking lot, a vehicle automatic identification system identifies a license plate number and a vehicle type, the vehicle owner needs to shake down a vehicle window to identify a face, attribute relation between the vehicle and the vehicle owner is established, the vehicle owner downloads an App, an identification applet and the like at the entrance through a code scanning mode or a Bluetooth transmission mode, parking space information and path information are checked, a vehicle gear lever at the entrance is lifted, the vehicle enters, the vehicle owner inquires the parking space information, and the vehicle owner parks in the parking space according to route planning; when a vehicle needs to be taken out, the vehicle is found according to APP or small program information prompt, the vehicle is driven to an outlet according to route planning, a vehicle owner shakes down a vehicle window to perform face recognition, a vehicle gear is lifted, and the vehicle is driven out of a parking lot.
To sum up, in this embodiment, according to the intelligent parking device based on the visual image algorithm of this embodiment, the intelligent parking device based on the visual image algorithm provided by this embodiment adopts a combination of an automatic license plate recognition system and a face recognition technology, and can link a car owner with a vehicle to prevent a car theft behavior, and a dynamic video analysis system can analyze a vehicle running route to provide a nearest parking space, so that the car owner can park quickly, thereby saving a lot of time.
The above description is only for the purpose of illustrating the present invention and is not intended to limit the scope of the present invention, and any person skilled in the art can substitute or change the technical solution of the present invention and its conception within the scope of the present invention.

Claims (8)

1. The utility model provides an intelligence parking equipment based on visual image algorithm, its characterized in that, includes treater, storage owner vehicle information's database, dynamic video analytic system, identification system, route planning module, timing module and mobile client, dynamic video analytic system includes vision sensor, all-round camera and carries out the video acquisition module that the video was caught through the camera, identification system includes license plate identification module, face identification module and radio frequency card identification module, the treater respectively with database, dynamic video analytic system, identification system route planning system timing module link to each other, the database respectively with dynamic video analytic system, identification system, route planning module link to each other.
2. The intelligent parking device based on the visual image algorithm as claimed in claim 1, wherein: the database stores owner information, vehicle information and historical parking records, the owner information comprises a main phone number, a face image and parking fees, and the vehicle information comprises license plate numbers and vehicle types.
3. The intelligent parking device based on the visual image algorithm as claimed in claim 1, wherein: the video acquisition module records the dynamic information of the vehicle by adopting a multi-camera information fusion technology and a video tracking technology.
4. The intelligent parking device based on the visual image algorithm as claimed in claim 3, wherein: the multi-camera information fusion technology performs motion segmentation, object classification and behavior understanding through a plurality of cameras, and performs video fusion on a plurality of videos.
5. The intelligent parking device based on the visual image algorithm as claimed in claim 3, wherein: the video tracking technology adopts Kalman filtering and a condensation algorithm and tracks the motion track of the vehicle based on a multi-camera information fusion technology.
6. The intelligent parking device based on the visual image algorithm as claimed in claim 1, wherein: the route planning module adopts dijk-stra algorithm, comprises the number of road sections participating in calculation, reading efficiency of topological data and sorting efficiency of a temporary table, and provides a plurality of routes for vehicle owners to select by taking route rationality, time consumption, space consumption and hardware cost as weights.
7. The intelligent parking device based on the visual image algorithm as claimed in claim 1, wherein: the parking lot entrance is equipped with license plate discernment camera and face identification camera, all is equipped with the camera on every parking stall.
8. The intelligent parking device based on the visual image algorithm as claimed in claim 1, wherein: the mobile client comprises a vehicle-mounted system, a mobile phone APP and a small program and is used for providing vacant parking space information, route information and parking time cost information for a vehicle owner.
CN201910167213.6A 2019-03-06 2019-03-06 Intelligent parking device based on visual image algorithm Pending CN111666784A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910167213.6A CN111666784A (en) 2019-03-06 2019-03-06 Intelligent parking device based on visual image algorithm

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910167213.6A CN111666784A (en) 2019-03-06 2019-03-06 Intelligent parking device based on visual image algorithm

Publications (1)

Publication Number Publication Date
CN111666784A true CN111666784A (en) 2020-09-15

Family

ID=72381844

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910167213.6A Pending CN111666784A (en) 2019-03-06 2019-03-06 Intelligent parking device based on visual image algorithm

Country Status (1)

Country Link
CN (1) CN111666784A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113053133A (en) * 2021-03-10 2021-06-29 江西岱泊智能科技有限公司 A vehicle information acquisition intelligent terminal for open road parking stall

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113053133A (en) * 2021-03-10 2021-06-29 江西岱泊智能科技有限公司 A vehicle information acquisition intelligent terminal for open road parking stall
CN113053133B (en) * 2021-03-10 2023-03-24 江西岱泊智能科技有限公司 A vehicle information acquisition intelligent terminal for open road parking stall

Similar Documents

Publication Publication Date Title
CN108765976B (en) Roadside parallel parking information management system and method
JP6503218B2 (en) Driving support system, driving support device and driving support method
CN102819965B (en) Parking guidance and searching system for parking lot
CN110766975B (en) Intelligent vehicle searching management method and system for parking lot
CN106781685A (en) A kind of city intelligent shutdown system that robot is managed based on parking garage
CN102436760A (en) Intelligent parking lot method and system
CN108986539A (en) Parking management system, method, vehicle information collecting device and management server
CN111444798B (en) Identification method and device for driving behavior of electric bicycle and computer equipment
CN104217607B (en) A kind of parking lot reverse car seeking method and device using compound RFID card
CN112820137B (en) Parking lot management method and device
CN105046966A (en) System and method for automatically detecting illegal parking behaviors in drop-off areas
CN114202959B (en) Foreign vehicle management method and system
CN105118305A (en) Vehicle management platform of outdoor parking lot exit
CN115311894A (en) Intelligent parking management method, system, terminal and medium based on big data analysis
CN116092206A (en) Identification and charging system and method for unattended vehicle entering and exiting parking lot
CN110930764A (en) Roadside parking detection method based on inspection method
CN110310378A (en) A kind of open type parking ground parking charge method and system based on double mirror
CN113706888A (en) Road parking berth system based on RFID radio frequency card and berth patrol method
CN204856897U (en) It is detection device violating regulations in abscission zone territory that motor vehicle stops promptly
CN111223303B (en) Charging pile parking space management method, device and system
CN114694095A (en) Method, device, equipment and storage medium for determining parking position of vehicle
CN111260953A (en) In-road parking management method, device and system
CN111666784A (en) Intelligent parking device based on visual image algorithm
CN113421433A (en) Regional video parking guide system and parking guide method
CN111785068A (en) Garage management system

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20200915

WD01 Invention patent application deemed withdrawn after publication