CN113177447A - Reverse vehicle searching method based on computer vision - Google Patents
Reverse vehicle searching method based on computer vision Download PDFInfo
- Publication number
- CN113177447A CN113177447A CN202110420107.1A CN202110420107A CN113177447A CN 113177447 A CN113177447 A CN 113177447A CN 202110420107 A CN202110420107 A CN 202110420107A CN 113177447 A CN113177447 A CN 113177447A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- license plate
- parking lot
- plate information
- underground parking
- 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
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/54—Surveillance or monitoring of activities, e.g. for recognising suspicious objects of traffic, e.g. cars on the road, trains or boats
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/23—Updating
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/625—License plates
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Quality & Reliability (AREA)
- Remote Sensing (AREA)
- Traffic Control Systems (AREA)
Abstract
A reverse vehicle searching method based on computer vision belongs to the field of intelligent transportation. The invention solves the problems of complex vehicle searching method and high cost caused by the fact that a large amount of additional equipment needs to be installed in the existing vehicle searching method. In the vehicle positioning, a special reverse vehicle searching terminal is not required to be arranged in the parking lot, and whether the vehicle is parked in the parking space or not is judged only by utilizing the image extracted by the lane camera arranged in the parking lot, so that a large amount of cost of the parking lot is saved, and the time for a vehicle owner to search the terminal in the vehicle searching process is saved. Moreover, the vehicle owner does not need to purchase other equipment by himself, the optimal path of the vehicle can be obtained by entering the reverse vehicle searching small program through the smart phone, the path is clearer and the vehicle searching method is simple. The invention can be used for reverse vehicle searching in underground parking lots.
Description
Technical Field
The invention belongs to the field of intelligent transportation, and particularly relates to a reverse vehicle searching method based on computer vision.
Background
With the increasing of the total quantity of private cars in China, the number of underground parking lots is also increased rapidly, and the scale is enlarged continuously. At present, most underground parking lots have large areas and lots of parking spaces, light rays in the parking lots are poor, and indication marks are not clear and standardized enough, so that the direction sense of many vehicle owners in the underground parking lots is poor, the accurate positions of vehicle parking are often forgotten, and specific vehicle searching routes are not clear. The phenomenon of 'difficulty in finding the car reversely' causes the waste of time of car owners and brings great inconvenience to the life of the car owners. Use the rush-hour in the parking area, if the parking stall does not reach the space-time and come out, will cause the waste of parking area resource, aggravate the jam in the parking area, reduce the rate of utilization in parking area to a certain extent.
In order to help car owners and parking lots solve the problem, many indoor positioning technologies are as follows: ultrasonic, infrared, bluetooth, WI-FI, ZigBee, and the like are used in vehicle positioning. The existing vehicle positioning method and the reverse vehicle searching method are mainly applied as follows:
blue tooth positioning method: the automobile is internally provided with a signal transmitting module, and the top of the automobile is provided with a transmitting antenna capable of amplifying signals. When a vehicle is searched, a vehicle owner needs to open the Bluetooth of the smart phone, the portable monitoring lateral device of the vehicle owner can effectively identify the transmitting antenna signal, judge the accurate position of the vehicle and finally transmit the monitored position information of the vehicle to the smart phone of the vehicle owner. The portable monitoring side equipment can be embedded into the car key of the car owner (the dragon-shaped automatic car-searching technology is applied to the intelligent network system of the car [ J ]). The method needs the owner to purchase special equipment by himself, and needs to further modify the key of the owner, which is not easy to popularize.
Ultrasonic vehicle inspection method: the ultrasonic wave device is divided into a transmitting device and a receiving device, when the ultrasonic wave transmitting device transmits ultrasonic waves to the parking space, the receiving device calculates the distance between the parking space and the ultrasonic wave transmitting device according to the time length of the ultrasonic wave reflected by the parking space by a formula, and therefore whether vehicles exist in the parking space is determined. When parking is carried out in a parking space, the ultrasonic transmitting device starts to transmit ultrasonic waves and calculates time, the ultrasonic waves can generate light waves when encountering an obstacle in the transmitting process, and the reflection receiving device calculates the time and stops when receiving echo information, so that the distance can be obtained, and the existence of a vehicle in the parking space is judged (Wangmilitary space, research on an intelligent parking lot management system based on ZigBee [ D ]). This method requires an additional ultrasonic device and is cost-prohibitive.
RSSI positioning method: lay the parking stall in the rational position of parking stall and detect the label, the parking stall detects the label and changes according to certain time interval with certain signal strength to roadside node transmission signal, the received signal strength of roadside node shelters from the thing and on the transmission distance and the channel according to the signal, it is fixed when transmission distance, shelter from on the channel and will become the main factor who influences RSSI, shelter from the thing and shelter from the channel more, radio frequency signal is poor the more to the penetrability that shelters from the thing, signal attenuation just more, RSSI just is lower. Therefore, the existence of the shelter can be judged through the analysis of the RSSI, and then the occupation condition of the parking space (Chen, Zhouyi, Lian, the design of the integral scheme of the intelligent parking management and service system [ J ]) based on the Internet of things and the image recognition technology is further judged. The application RSSI technique needs to arrange the parking stall label in the parking area, and is with higher costs, and the degree of accuracy of RSSI location technique is easily influenced by the environment simultaneously.
A visible light indoor parking lot vehicle searching method based on LED lighting light comprises the following steps: when an automobile owner enters an indoor parking lot and positioning software is started, a front-mounted camera of the smart phone is started to capture a stripe image of a visible light positioning LED lamp of the parking lot, background light generated by a non-visible light positioning LED lamp is filtered through image processing to avoid interference, the stripe image is preprocessed through a lightweight image processing algorithm, a stripe region is positioned and extracted, and a UID corresponding to the lamp is obtained through decoding, the current position of the automobile owner is calculated through a positioning algorithm based on visual analysis and displayed on a software terminal, and therefore positioning is achieved. This method also requires a parking lot to purchase the device, which is too costly.
The method for searching the path by the inquiry terminal comprises the following steps: the inquiry machine is arranged at each main entrance and exit of the parking lot, a vehicle owner can inquire the position of the vehicle by inputting the license plate number, and the system software can present the parking position and the shortest vehicle searching route (Wanglingyu-Ruizhou big data application display convention center intelligent parking management system shallow talking [ J ]). In the method, equipment needs to be additionally arranged in the parking lot, and the car owner needs to search for the reverse car searching terminal in the parking lot, so that a path can be forgotten in the car searching process, the time of the car owner is not saved to the maximum extent, and the life convenience is brought.
Disclosure of Invention
The invention aims to solve the problems that the existing vehicle searching method needs to install additional equipment, so that the vehicle searching method is complex and high in cost, and provides a reverse vehicle searching method based on computer vision.
The technical scheme adopted by the invention for solving the technical problems is as follows: a reverse vehicle searching method based on computer vision specifically comprises the following steps:
firstly, detecting license plate information on a vehicle entering an underground parking lot by license plate detection equipment at an entrance;
secondly, starting the cameras which are nearest to the front, the left and the right of the entrance in each direction, respectively operating a license plate recognition algorithm on the images captured by the started cameras, and recording camera numbers corresponding to the images containing the license plate information detected in the first step and the license plate information detected in the first step into a memory;
thirdly, continuously starting the cameras which are most adjacent to the cameras in the front, back, left and right directions and recorded in the second step, if the license plate information detected in the first step does not appear in the images captured by the cameras in the continuous T time, the vehicle corresponding to the license plate information finishes parking, and the serial number of the last camera capturing the license plate information and the license plate information are uploaded to a cloud database; taking the coverage area of the last camera capturing the license plate information as the parking position of the vehicle corresponding to the license plate information;
if not, continuously starting the cameras which are closest to the cameras capturing the license plate information in the front direction, the rear direction, the left direction and the right direction, and continuously tracking the vehicle corresponding to the license plate information;
step four, repeating the process from the step one to the step three, and recording the parking position of each vehicle entering the underground parking lot;
drawing an underground parking lot map according to the underground parking lot plan;
sixthly, dividing the underground parking area into sub-areas, setting the central point of each sub-area as a key node, setting the position of each elevator as a key node, and setting each road intersection as a secondary key node;
sequentially marking the key nodes and the secondary key nodes with sequence numbers, and obtaining pixel coordinates of each key node and each secondary key node in the underground parking lot map;
step seven, establishing a undirected network diagram
According to the pixel coordinates of the key nodes and the secondary key nodes in the underground parking lot map, all the key nodes and the secondary key nodes are respectively used as nodes, and edge adding operation is carried out between every two adjacent nodes;
step eight, inputting license plate information of the vehicle to be searched and the current node position of the user through a user side small program, outputting an optimal path from the current position of the user to the parking position of the vehicle to be searched according to the parking position of the vehicle to be searched recorded in the cloud database by the small program and the undirected network diagram established in the step seven;
displaying the output optimal path in the underground parking lot map, and searching a parking position according to the optimal path after a user checks the optimal path in the underground parking lot map through a small program;
and step nine, detecting the license plate information of the vehicle driven out of the underground parking lot by the license plate detection equipment at the outlet, and deleting the license plate information from the information recorded in the cloud database.
The invention has the beneficial effects that: the invention provides a reverse vehicle searching method based on computer vision, which is characterized in that in vehicle positioning, a special reverse vehicle searching terminal is not required to be arranged in a parking lot, and whether a vehicle is parked in a parking space is judged only by utilizing an image extracted by a lane camera arranged in the parking lot, so that a large amount of cost of the parking lot is saved, and the time for a vehicle owner to search the terminal in the vehicle searching process is saved. Moreover, the vehicle owner does not need to purchase other equipment by himself, the optimal path of the vehicle can be obtained by entering the reverse vehicle searching small program through the smart phone, the path is clearer and the vehicle searching method is simple.
Meanwhile, the vehicle owner can check the path at any time, and the forgetting problem caused by obtaining the optimal path at the reverse vehicle searching terminal is avoided.
Drawings
Fig. 1 is a flow chart of a reverse car-finding method based on computer vision according to the invention.
Detailed Description
First embodiment this embodiment will be described with reference to fig. 1. The reverse vehicle searching method based on the computer vision in the embodiment specifically comprises the following steps:
firstly, detecting license plate information on a vehicle entering an underground parking lot by license plate detection equipment at an entrance;
secondly, starting the cameras which are nearest to the front, the left and the right of the entrance in each direction, respectively operating a license plate recognition algorithm on the images captured by the started cameras, and recording camera numbers corresponding to the images containing the license plate information detected in the first step and the license plate information detected in the first step into a memory;
thirdly, continuously starting the cameras which are most adjacent to the cameras in the front, back, left and right directions and recorded in the second step, if the license plate information detected in the first step does not appear in the images captured by the cameras in the continuous T time, the vehicle corresponding to the license plate information finishes parking, and the serial number of the last camera capturing the license plate information and the license plate information are uploaded to a cloud database; taking the coverage area of the last camera capturing the license plate information as the parking position of the vehicle corresponding to the license plate information;
if not, continuously starting the cameras which are closest to the cameras capturing the license plate information in the front direction, the rear direction, the left direction and the right direction, and continuously tracking the vehicle corresponding to the license plate information;
step four, repeating the process from the step one to the step three, and recording the parking position of each vehicle entering the underground parking lot;
drawing an underground parking lot map according to the underground parking lot plan;
sixthly, dividing the underground parking area into sub-areas, setting the central point of each sub-area as a key node, setting the position of each elevator as a key node, and setting each road intersection as a secondary key node;
sequentially marking the key nodes and the secondary key nodes with sequence numbers, and obtaining pixel coordinates of each key node and each secondary key node in the underground parking lot map;
step seven, establishing a undirected network diagram
According to the pixel coordinates of the key nodes and the secondary key nodes in the underground parking lot map, all the key nodes and the secondary key nodes are respectively used as nodes, and edge adding operation is carried out between every two adjacent nodes;
step eight, inputting license plate information of the vehicle to be searched and the current node position of the user through a user side small program, outputting an optimal path from the current position of the user to the parking position of the vehicle to be searched according to the parking position of the vehicle to be searched recorded in the cloud database by the small program and the undirected network diagram established in the step seven;
displaying the output optimal path in the underground parking lot map, and searching a parking position according to the optimal path after a user checks the optimal path in the underground parking lot map through a small program;
and step nine, detecting the license plate information of the vehicle driven out of the underground parking lot by the license plate detection equipment at the outlet, and deleting the license plate information from the information recorded in the cloud database.
The second embodiment is as follows: the difference between the present embodiment and the specific embodiment is that the license plate recognition algorithm is an open source character recognition method based on Baidu paddlehub.
The third concrete implementation mode: the difference between the present embodiment and the first embodiment is that cameras are disposed at the intersections of the main lines and the roads in the underground parking lot.
The fourth concrete implementation mode: the first difference between the present embodiment and the specific embodiment is that the sub-areas of the underground parking lot are divided, which specifically includes: the area covered by each camera in the underground parking lot is divided into a sub-area.
The fifth concrete implementation mode: the first difference between the present embodiment and the specific embodiment is that the sub-areas of the underground parking lot are divided, which specifically includes: dividing every N parking spaces into one sub-area.
In the invention, the value of N can be set to be 2-6, so that the owner can recognize the own vehicle in the sub-area.
The sixth specific implementation mode: the present embodiment is different from the first embodiment in that the license plate information is a license plate number of a vehicle.
The seventh embodiment: the difference between this embodiment and the specific embodiment is that the outputting of the optimal path from the current position of the user to the parking position of the vehicle to be searched according to the undirected network diagram established in the seventh step is implemented by a Dijkstra algorithm.
The specific implementation mode is eight: the present embodiment is different from the first embodiment in that T is 50 s.
Examples
The invention discloses a reverse vehicle searching method based on computer vision, which comprises the following steps:
step one, initializing and recording license plate information of vehicles entering a garage by an entrance camera
And continuously capturing photos by a camera at the entrance of the underground parking lot, operating a license plate recognition algorithm on the photos to extract license plate numbers, establishing new entries of a database by taking the license plate numbers as main keys, and inserting license plates into the internal storage license plate information dictionary. The garage door area is set as an area of interest (area where the amount of vehicles may appear). The license plate recognition algorithm is based on a Baidu paddlehub open source character recognition model, character string recognition is carried out on the picture, the character strings obtained through detection are matched with the license plates obtained through garage entrance detection one by one, and the actual license plates are considered to be detected if certain similarity is exceeded.
Step two, updating the vehicle position information
And running a license plate recognition algorithm on a single frame of video shot by the cameras in all the interest areas. If the license plate information is identified by the camera through a license plate identification algorithm within 2 minutes, recording the number of the camera capable of identifying the license plate and the identified license plate information into a memory, setting the area around the identified license plate area as a new interesting area, and iteratively replacing the current interesting area; if the license plate information can be identified within 2 minutes without the camera, the license plate number identified by the camera in the memory last and the camera number identifying the license plate are uploaded to the database, the license plate number is deleted in the memory, the vehicle is shown to be parked completely, and the tracking of the vehicle position is stopped. If the current vehicle possible driving area is the interest area (possible driving area) of other vehicles at the same time, the interest area is not deleted repeatedly when the interest area is detected and updated. When a certain area of the current vehicle possible driving area is not possible to be an area of interest (possible driving area) of other vehicles, the area is set to be cancelled as the current vehicle area of interest (possible driving area) after iteration. And after the iteration is finished, operating the license plate recognition algorithm of the cameras in all the current vehicle interest areas (possible driving areas) again.
Step three, judging the final state of the vehicle
When the license plate does not appear in the picture captured by the camera for a period of time, the license plate is considered to be stopped at the parking space or driven out of the garage. If the license plate number is detected by the camera at the exit during and after the time, the vehicle is considered to exit the garage, and the license plate information of the vehicle in the database is deleted. If the license plate number is not detected by the exit camera in the period and in a later period, the vehicle is considered to be parked on the parking space, the parking information of the vehicle is recorded into the cloud database, and the license plate information in the memory is deleted.
Fourthly, manufacturing a two-dimensional plane map of the parking lot
And (4) according to the parking lot plane map (if the plane map is not available, a draft is drawn by measuring in advance), manufacturing the parking lot map in a jpg format by adopting drawing software according to a certain proportion.
Step five, selecting key nodes in the map and obtaining coordinates
Dividing all road sections into a plurality of areas according to the road sections which can be detected by the cameras of the parking lot, selecting the central point of each area as a key node, setting the key node at each elevator of the parking lot, and setting secondary key nodes at road intersections. The key nodes and the secondary key nodes are sequentially marked with serial numbers. A PIL library is introduced into a python compiler, and the created map is organized by an image in order to obtain pixel coordinates of a node.
Step six, establishing a network graph among nodes
And (2) importing a network library into a python compiler, establishing an empty undirected graph through G ═ network x.graph (), adding points in the step two into the network graph, carrying out edge adding operation in the network graph by every two points which can be reached in a straight line (without barriers in the middle), and setting the weight (length) of each edge as the distance between two points in the real parking lot.
Step seven, determining dijkstra algorithm parameters
Defining a function defDijkstra (G, start, end) in the algorithm, wherein the parameter G is the network graph determined in the step six; the start is the starting point of path planning, and is obtained by a user through an identification number (a serial number of a key node) of a highlighted area of the parking lot, and an applet is input; and end is the path planning end point and is obtained from the database. The optimal path (list of node sequences) between every two key points is obtained by dijkstra algorithm.
Step eight, displaying the path in a map
And (4) importing a pylab library into a python compiler, and sequentially connecting the nodes obtained in the step seven through a plot command and displaying the nodes in a map.
The above-described calculation examples of the present invention are merely to explain the calculation model and the calculation flow of the present invention in detail, and are not intended to limit the embodiments of the present invention. It will be apparent to those skilled in the art that other variations and modifications of the present invention can be made based on the above description, and it is not intended to be exhaustive or to limit the invention to the precise form disclosed, and all such modifications and variations are possible and contemplated as falling within the scope of the invention.
Claims (8)
1. A reverse vehicle searching method based on computer vision is characterized by comprising the following steps:
firstly, detecting license plate information on a vehicle entering an underground parking lot by license plate detection equipment at an entrance;
secondly, starting the cameras which are nearest to the front, the left and the right of the entrance in each direction, respectively operating a license plate recognition algorithm on the images captured by the started cameras, and recording camera numbers corresponding to the images containing the license plate information detected in the first step and the license plate information detected in the first step into a memory;
thirdly, continuously starting the cameras which are most adjacent to the cameras in the front, back, left and right directions and recorded in the second step, if the license plate information detected in the first step does not appear in the images captured by the cameras in the continuous T time, the vehicle corresponding to the license plate information finishes parking, and the serial number of the last camera capturing the license plate information and the license plate information are uploaded to a cloud database; taking the coverage area of the last camera capturing the license plate information as the parking position of the vehicle corresponding to the license plate information;
if not, continuously starting the cameras which are closest to the cameras capturing the license plate information in the front direction, the rear direction, the left direction and the right direction, and continuously tracking the vehicle corresponding to the license plate information;
step four, repeating the process from the step one to the step three, and recording the parking position of each vehicle entering the underground parking lot;
drawing an underground parking lot map according to the underground parking lot plan;
sixthly, dividing the underground parking area into sub-areas, setting the central point of each sub-area as a key node, setting the position of each elevator as a key node, and setting each road intersection as a secondary key node;
sequentially marking the key nodes and the secondary key nodes with sequence numbers, and obtaining pixel coordinates of each key node and each secondary key node in the underground parking lot map;
step seven, establishing a undirected network diagram
According to the pixel coordinates of the key nodes and the secondary key nodes in the underground parking lot map, all the key nodes and the secondary key nodes are respectively used as nodes, and edge adding operation is carried out between every two adjacent nodes;
step eight, inputting license plate information of the vehicle to be searched and the current node position of the user through a user side small program, outputting an optimal path from the current position of the user to the parking position of the vehicle to be searched according to the parking position of the vehicle to be searched recorded in the cloud database by the small program and the undirected network diagram established in the step seven;
displaying the output optimal path in the underground parking lot map, and searching a parking position according to the optimal path after a user checks the optimal path in the underground parking lot map through a small program;
and step nine, detecting the license plate information of the vehicle driven out of the underground parking lot by the license plate detection equipment at the outlet, and deleting the license plate information from the information recorded in the cloud database.
2. The computer vision-based reverse car finding method according to claim 1, wherein the license plate recognition algorithm is a Baidu paddlehub-based open source character recognition method.
3. The reverse vehicle searching method based on the computer vision is characterized in that cameras are arranged at the positions of each trunk line and each road intersection of the underground parking lot.
4. The reverse vehicle searching method based on computer vision is characterized in that the underground parking lot area is divided into sub-areas, which is specifically that: the area covered by each camera in the underground parking lot is divided into a sub-area.
5. The reverse vehicle searching method based on computer vision is characterized in that the underground parking lot area is divided into sub-areas, which is specifically that: dividing every N parking spaces into one sub-area.
6. The reverse vehicle searching method based on computer vision of claim 1, wherein the license plate information is a license plate number of the vehicle.
7. The computer vision-based reverse vehicle searching method according to claim 1, wherein the step of outputting the optimal path from the current position of the user to the parking position of the vehicle to be searched according to the undirected network graph established in the step seven is realized by a Dijkstra algorithm.
8. The reverse vehicle seeking method based on computer vision according to claim 1, wherein the value of T is 50 s.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110420107.1A CN113177447A (en) | 2021-04-19 | 2021-04-19 | Reverse vehicle searching method based on computer vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110420107.1A CN113177447A (en) | 2021-04-19 | 2021-04-19 | Reverse vehicle searching method based on computer vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113177447A true CN113177447A (en) | 2021-07-27 |
Family
ID=76923798
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110420107.1A Pending CN113177447A (en) | 2021-04-19 | 2021-04-19 | Reverse vehicle searching method based on computer vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113177447A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103440781A (en) * | 2013-08-28 | 2013-12-11 | 苏州智蝶科技有限公司 | Parking lot reverse car seeking management system based on fuzzy positioning and implementation method of parking lot reverse car seeking management system |
| CN103824472A (en) * | 2014-02-28 | 2014-05-28 | 青岛英飞凌电子技术有限公司 | Parking lot video management system for achieving forward parking guiding function and reverse vehicle finding function |
| CN104933886A (en) * | 2015-07-03 | 2015-09-23 | 长沙地大物泊网络科技有限公司 | Two-dimension code scanning reverse vehicle-searching system based on intelligent terminal |
| CN106297362A (en) * | 2016-08-17 | 2017-01-04 | 重庆元云联科技有限公司 | The method of parking lot reverse car seeking |
-
2021
- 2021-04-19 CN CN202110420107.1A patent/CN113177447A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103440781A (en) * | 2013-08-28 | 2013-12-11 | 苏州智蝶科技有限公司 | Parking lot reverse car seeking management system based on fuzzy positioning and implementation method of parking lot reverse car seeking management system |
| CN103824472A (en) * | 2014-02-28 | 2014-05-28 | 青岛英飞凌电子技术有限公司 | Parking lot video management system for achieving forward parking guiding function and reverse vehicle finding function |
| CN104933886A (en) * | 2015-07-03 | 2015-09-23 | 长沙地大物泊网络科技有限公司 | Two-dimension code scanning reverse vehicle-searching system based on intelligent terminal |
| CN106297362A (en) * | 2016-08-17 | 2017-01-04 | 重庆元云联科技有限公司 | The method of parking lot reverse car seeking |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111081047A (en) | Accurate intelligent parking management method and management system based on photoelectric image processing | |
| CN105405317B (en) | A kind of parking guidance system based on Bluetooth of mobile phone | |
| CN106097755A (en) | For identifying the method parked place and/or vacate place | |
| TW201742031A (en) | An intelligent parking system and method | |
| CN110853391A (en) | Intelligent shared parking system | |
| CN111311957A (en) | Parking guidance system based on RFID and unmanned aerial vehicle and working method | |
| CN105528912A (en) | Indoor parking stall recommendation method and system | |
| CN111445703A (en) | Intelligent parking lot system and method based on image recognition | |
| CN205354375U (en) | Inducible system of parking based on bluetooth of mobile phone | |
| CN111932934A (en) | Intelligent parking lot in-and-out vehicle management system based on big data | |
| CN110942662A (en) | Real-time reverse vehicle searching system and method for parking lot | |
| CN212873756U (en) | Reverse vehicle searching system | |
| JP3402263B2 (en) | Traffic information management device and traffic information management method | |
| JPH0933232A (en) | Object observation method and object observation apparatus using this method, as well as traffic-flow measuring apparatus using this apparatus, and parking-lot observation apparatus | |
| CN115512565A (en) | Indoor navigation method for indoor parking lot and parking management system | |
| JP3502156B2 (en) | Traffic monitoring system | |
| Someswar et al. | Design & development of an autonomic integrated car parking system | |
| CN112990759A (en) | Digital twin-based data processing system | |
| CN113762250A (en) | Vehicle searching method, device, equipment and computer readable storage medium | |
| CN113177447A (en) | Reverse vehicle searching method based on computer vision | |
| CN109031262B (en) | Positioning vehicle searching system and method thereof | |
| US20220412767A1 (en) | Spotfinder | |
| CN115578883A (en) | Parking space allocation and safety system of intelligent three-dimensional parking lot | |
| CN113393699A (en) | Intelligent parking lot system and method | |
| CN209765742U (en) | Intelligent parking management system based on Beidou position service |
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 |