CN107067794B - Indoor vehicle positioning and navigation system and method based on video image processing - Google Patents
Indoor vehicle positioning and navigation system and method based on video image processing Download PDFInfo
- Publication number
- CN107067794B CN107067794B CN201611019433.7A CN201611019433A CN107067794B CN 107067794 B CN107067794 B CN 107067794B CN 201611019433 A CN201611019433 A CN 201611019433A CN 107067794 B CN107067794 B CN 107067794B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- server
- user
- positioning
- indoor
- 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
- G08G1/14—Traffic control systems for road vehicles indicating individual free spaces in parking areas
- G08G1/141—Traffic control systems for road vehicles indicating individual free spaces in parking areas with means giving the indication of available parking spaces
- G08G1/143—Traffic control systems for road vehicles indicating individual free spaces in parking areas with means giving the indication of available parking spaces inside the vehicles
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—Instruments for performing navigational calculations
- G01C21/206—Instruments for performing navigational calculations specially adapted for indoor navigation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/08—Detecting or categorising vehicles
Abstract
The invention relates to an indoor vehicle positioning and navigation system and method based on video image processing, which comprises the following steps: the system comprises an image acquisition device, a server, a vehicle user terminal and communication equipment; the image acquisition device is used for capturing a moving vehicle and transmitting image data to a server positioned at a background in real time by utilizing communication equipment; an electronic map of an indoor parking lot is arranged in the vehicle-mounted user terminal, the electronic map is provided with position information of the image acquisition device, and the position information of the image acquisition device is marked in the server module; the moving vehicle information acquired by the image acquisition device is sent to the server through the communication equipment, and the position of the user vehicle is sent to the vehicle user terminal after the image processing of the background server.
Description
Technical Field
The invention belongs to the technical field of vehicle positioning in an intelligent parking system, and particularly relates to an indoor vehicle positioning navigation system and method based on video image processing, which realize real-time positioning.
Background
Along with the development of economic construction in China, the number of private cars is more and more, the requirement on large-scale parking lots is greater and greater, and meanwhile, the large-scale underground parking lots have the problems of complex landform, difficulty in finding vacant places, unclear lines and the like. Therefore, the improvement of the vehicle positioning accuracy and the parking space utilization rate of the underground parking lot is paid much attention to by various circles.
The GPS technology is a common navigation system, but when the GPS is applied indoors, signals are easy to be shielded, and positioning accuracy is greatly influenced or even fails; the iBeacon technology makes up the defects of the GPS technology, provides a low-cost and more power-saving positioning tracking technology for users, and can provide intelligent electronic service through a mobile terminal application program according to the positions and requirements of the users. The iBeacon is small, cannot be remotely controlled, is difficult to maintain and is difficult to manage; WIFI positioning is a positioning system implemented by using an existing wireless network, matching WIFI identifiers and related mobile devices such as mobile phones and computers, and combining corresponding positioning algorithms. At least one AP signal can be received at any point in the space in the city, the hotspot can transmit signals to the surroundings as long as the hotspot is electrified, no matter how encrypted, and the positioning has great errors.
Compared with the currently used indoor positioning navigation system, the system replaces a wireless local area network base station to transmit signals, has high transmission speed, and can upload data such as high-definition pictures and animations for a long time only in the place irradiated by indoor light. The receiving end of the system is selected as a camera, the relative far and near positions of the vehicle and the camera are determined through shooting of the camera, the defects of weak indoor signals and later maintenance are overcome, and accurate positioning can be achieved.
Disclosure of Invention
The invention aims to: the indoor vehicle positioning navigation system and method based on video image processing are provided, an indoor positioning technology based on a camera is adopted, the structure is simple, the applicability is wide, the operation is convenient, and the moving target detection and tracking under different environments can be popularized.
In order to achieve the above purpose, the invention provides a technical scheme for solving key technical problems:
an indoor vehicle positioning and navigation system based on video image processing is characterized by comprising: the system comprises an image acquisition device, a server, a vehicle user terminal and communication equipment; the image acquisition device is used for capturing a moving vehicle and transmitting image data to a server positioned at a background in real time by utilizing communication equipment; an electronic map of an indoor parking lot is arranged in the vehicle-mounted user terminal, the electronic map is provided with position information of the image acquisition device, and the position information of the image acquisition device is also marked in the server; the method comprises the steps that moving vehicle information acquired by an image acquisition device is sent to a server through communication equipment, the server at a background extracts and tracks a target vehicle through an image processing algorithm, the position of the vehicle is acquired through geometric relation operation, and then the position of a user vehicle is sent to a vehicle user terminal; meanwhile, the server also pushes parking space information, empty parking space information selected by the user and navigation information from the vehicle position of the user to the empty parking space position selected by the user to the user, so that real-time positioning and navigation of the vehicle in the parking lot are realized.
The image acquisition device consists of a plurality of cameras, and each camera is fixed and has a certain downward inclination angle.
In the server, the target vehicle is extracted and tracked through an image processing algorithm as follows:
(1) Modeling a Gaussian mixture model, namely, modeling each pixel by using K Gaussian distributions to form the Gaussian mixture model by calculating the average gray value and the pixel variance of each pixel in a video sequence image acquired by an image acquisition device in a period of time, wherein the K value is 3-5;
(2) Updating the model, and matching each pixel of the image frame with K Gaussian distributions in the Gaussian mixture model at the moment t, wherein for unmatched Gaussian distributions, the mean value and covariance matrix of the pixels are unchanged; the matched Gaussian distribution needs to update the parameters of each Gaussian distribution and the weight of each Gaussian distribution, the Gaussian distributions are sorted according to the weight, and new Gaussian distributions are added for model updating;
(3) Foreground detection, namely performing descending order sequencing on K Gaussian distributions of each pixel by using the ratio of the weight to the standard deviation obtained in the step (2), wherein the Gaussian distribution which is most likely to describe the stable background process is positioned in front of a sequence, the first B Gaussian distributions are taken as background models, each pixel value at the current moment is matched with the first B Gaussian distributions, matching exists, and the pixel point is a background point; otherwise, the pixel is detected as a moving target, namely a moving vehicle;
(4) And (4) tracking and positioning the target vehicle, taking the foreground obtained in the step (3) as initial target vehicle information, and combining a Camshift algorithm and a Kalman filter algorithm to realize accurate identification and positioning of the moving vehicle at the subsequent moment so as to complete tracking and positioning of the target vehicle.
In the server, the calculation process of obtaining the position coordinates of the vehicle through geometric relation calculation is as follows:
(1) Calculating a maximum included angle alpha and a minimum included angle beta between a vertical visual angle of the camera and a y axis of a ground plane according to the camera pin hole model, the camera position, the camera installation angle and the acquired basic parameters of the video image, and calculating an included angle gamma between the projection of the horizontal visual angle of the camera and the y axis of the ground plane;
α＝arctan(H/y 1 )
β＝arctan(H/(y 1 +y 2 ))
γ＝acrtan(x 1 /y 1 )
(2) Determining the actual coordinates P (x, y) of the target in the image according to the calculation result in the step (1), wherein x and y respectively represent the coordinate position of the moving target in the parking lot,
the vehicle user terminal is a mobile phone, a vehicle-mounted terminal and a platform computer.
The communication equipment is wireless communication equipment and is arranged in the user terminal.
An indoor vehicle positioning and navigation method based on video image processing is realized as follows: cameras are arranged at multiple positions of the indoor parking lot and are used for capturing moving vehicles and transmitting image data to a background server in real time by utilizing the cameras; an electronic map of an indoor parking lot is arranged in the vehicle-mounted user terminal, the electronic map is provided with position information of a camera, the position information of the camera is also marked on a server at the background, moving vehicle information acquired by the camera is sent to the server at the background, the server extracts and tracks a target vehicle through an image processing algorithm, the vehicle position is acquired through geometric relation operation, and the position of the user vehicle is sent to the vehicle user terminal; meanwhile, the server also pushes parking space information, empty parking space information selected by the user and navigation information from the vehicle position of the user to the empty parking space position selected by the user to the user, so that real-time positioning and navigation of the vehicle in the parking lot are realized.
Compared with the prior art, the invention has the advantages that: by adopting the technical scheme, the combination of the monitoring camera and the moving vehicle is adopted, the server side pushes the empty parking space information of the parking lot to the user, the position of the user vehicle and the empty parking space information selected by the user are determined, and the navigation information from the position of the user vehicle to the empty parking space position selected by the user is obtained. Thereby realize the real-time location navigation of vehicle in the parking area, for the car owner provides one kind and looks for the parking stall, the solution that intelligence was parkked, utilization parking area surveillance camera resource that can be fine improves parking efficiency, and the practicality is strong, can be better serve the car owner.
Drawings
FIG. 1 shows a schematic diagram of the measurement of the present invention;
fig. 2 shows a flow chart of the indoor vehicle positioning navigation of the present invention.
Detailed Description
The invention is further illustrated by the following embodiments in conjunction with the accompanying drawings.
As shown in fig. 1, the indoor vehicle positioning and navigation system based on video image processing of the present invention includes an image capturing device, a server, a vehicle user terminal (mobile phone, vehicle terminal, platform computer, etc.), and a communication device, wherein the image capturing device includes a plurality of cameras, each camera is fixed at a certain position and has a downward inclination angle (30-50 degrees). The indoor vehicle positioning navigation system provided by the invention has the following implementation processes: cameras are arranged at multiple positions of the indoor parking lot and are used for capturing moving vehicles and transmitting image data to a background server in real time by using the cameras; an electronic map of an indoor parking lot is arranged in the vehicle-mounted user terminal, the electronic map is provided with position information of a camera, the position information of the camera is also marked on a server at the background, moving vehicle information acquired by the camera is sent to the server at the background, the server extracts and tracks a target vehicle through an image processing algorithm, the vehicle position is acquired through geometric relation operation, and the position of the user vehicle is sent to the vehicle user terminal; meanwhile, the server also pushes parking space information, empty parking space information selected by the user and navigation information from the vehicle position of the user to the empty parking space position selected by the user to the user, so that real-time positioning and navigation of the vehicle in the parking lot are realized.
Geometric operations to obtain the vehicle position, fig. 1 shows the vehicle coordinates, and the camera is fixed and tilted downward at a certain angle (usually 30-50 degrees). The point P (x, y) is the vehicle position and P (μ, ν) is the image plane coordinates of its feature points on the camera imaging plane. H is the vertical distance of the camera to the ground, y 1 Is the closest distance, y, of the vertical view of the camera projected on the ground 1 +y 2 Is the farthest distance, x, projected on the ground from the vertical view of the camera 1 Is the distance that the horizontal viewing angle of the camera projects on the ground when its vertical viewing angle is closest to the ground. Alpha (alpha is more than 0 degree and less than 50 degrees) and beta (beta is more than 0 degree and less than 10 degrees) are respectively the maximum and minimum included angles between the vertical visual angle of the camera and the y axis of the ground plane, and gamma (gamma is more than 0 degree and less than 45 degrees) is the included angle between the projection of the horizontal visual angle of the camera and the y axis of the ground plane.
As shown in FIG. 1, H, y are known from the geometric relationship of the camera vacuum model 1 ，y 2 And x 1 In the case that the values of (a), (b), and (y) can be measured, the values of (a), (b), and (y) in the figure can be easily determined. After the obtained angles of alpha, beta and gamma, the horizontal and vertical coordinates x and y of the target P (x, y) in the coordinate system can be further obtained. The derivation relation is as follows:
α＝arctan(H/y 1 )
β＝arctan(H/(y 1 +y 2 ))
γ＝acrtan(x 1 /y 1 )
in the above formula, u and v represent the number of rows and columns of the target feature on the image plane, S x And S y Representing the total number of rows and columns in the x and y directions, respectively, of the image plane.
The image algorithm acquires a target to realize real-time tracking, according to a Gaussian mixture algorithm, the average gray value and the pixel variance of each pixel point in a video sequence image acquired by an image acquisition device in a period of time are calculated, K Gaussian distributions (the K value is 3-5) are formed for each pixel point to form a Gaussian mixture model for modeling, one part of the Gaussian distributions represents the pixel value of a moving target, and the other part of the Gaussian distributions represents the pixel value of a background. The gaussian distribution function can be represented by the following equation:
in the formula X i,t D represents X as a variable of the color point i,t Dimension of (d =1 is usually taken for mixed gaussian background modeling of gray scale images), μ i,t Is mean value, Σ i,t Is a covariance matrix, and
(ω i,t as a weight).
Then updating a Gaussian model, matching each pixel of the current frame with K Gaussian distributions in the Gaussian mixture model at the moment t, and keeping the mean value and covariance matrix of unmatched Gaussian distributions unchanged; the matched gaussian distributions need to update the parameters of each gaussian distribution and the weights of the gaussian distributions, and the updated gaussian distributions can update the mean and standard deviation according to the following formula:
ω i,t ＝(1-α)ω i,t-1 +αM i,t
μ i,t ＝(1-β)μ i,t-1 +β
wherein alpha (alpha is more than or equal to 0 and less than or equal to 1) is a self-defined updating rate, beta is a parameter learning rate, and sigma is i,t Is the standard deviation. And if the color variable of the current pixel point is not matched with all the distributions of the Gaussian mixture model, replacing the model with the minimum weight in the Gaussian mixture model with a new model. New model with X i,t Is taken as the mean value and initialized to a larger standard deviation sigma 0 And a smaller weight. The remaining models remain unchanged with the original parameters, but the weights decay and are updated according to the following formula: omega i,t ＝(1-α)ω i,t-1
The detection extraction of the moving vehicle is foreground detection, all parameters of the Gaussian mixture model are updated according to the new pixel values
The K Gaussian distributions of each pixel are sorted in a descending order according to the ratio, and since the Gaussian distribution which is most likely to describe the stable background process is positioned in front of the sequence, the first B Gaussian distributions are taken as background models, and the rest are taken as foreground models.
Where τ is the threshold of the full value (typically 0.7), representing the minimum of the sum of the gaussian distribution weights that can describe the scene background. Every pixel value X of the current time is compared i,t Matching with the obtained first B Gaussian distributions, wherein the matching exists, and the pixel point is a background point; otherwise, the pixel is detected as a moving object, namely a moving vehicle.
b represents the number of Gaussian distributions, t represents time, i represents a Gaussian component, w i,j The weighting coefficient, i.e. the weight, of the ith gaussian component at time t is represented.
And finally, tracking and positioning the target vehicle, acquiring initial target vehicle information according to the moving foreground target acquired by foreground detection, and accurately identifying and positioning the moving vehicle at the subsequent moment by combining a Camshift algorithm and a Kalman filter algorithm so as to finish the tracking and positioning of the target vehicle.
And positioning and displaying the moving vehicle acquired in real time and the vehicle coordinate information acquired through the geometric relation at a user vehicle terminal, and acquiring the empty parking space information of the parking lot. As shown in fig. 2, the whole process is that a vehicle enters a background of a parking lot and empty parking space information is sent to a user, the user selects an empty parking space according to the coordinates of the vehicle and the empty parking space information sent by the background, and the system helps the user to realize vehicle positioning and navigation.
As an improvement of the invention, the server stores the parking space information in the background, when a user needs to find a vehicle, a request can be sent to the server, the server retrieves the parking space information bound with the information of the vehicle to be checked and sends the parking space information to the user, a navigation route is pushed to the user according to the position of the user, and the user terminal displays the parking space information and the navigation information. Thereby providing a possibility for a user to find the vehicle conveniently.
Furthermore, according to the parking lot information acquired by the camera, parking space information and vehicle movement information can be judged, real-time updating of parking spaces in the parking lot is guaranteed, and parking of other users is facilitated. In addition, the optimal selection based on the distance parking can be pushed to the car owner according to the distance between the car owner and the empty parking space or the distance between the car owner and the parking lot exit, so that the car owner can conveniently leave the parking lot while the parking time of the car owner is saved.
The above examples and further modified illustrations of the present invention are provided only for the purpose of describing the present invention, and are not intended to limit the scope of the present invention. The scope of the invention is defined by the appended claims. Various equivalent substitutions and modifications can be made without departing from the spirit and principles of the invention, and are intended to be within the scope of the invention.
Claims (5)
1. An indoor vehicle positioning and navigation system based on video image processing is characterized by comprising: the system comprises an image acquisition device, a server, a vehicle user terminal and communication equipment; the image acquisition device is used for capturing a moving vehicle and transmitting image data to a server positioned at a background in real time by utilizing communication equipment; an electronic map of an indoor parking lot is arranged in the vehicle-mounted user terminal, the electronic map is provided with position information of the image acquisition device, and the position information of the image acquisition device is also marked in the server; the method comprises the steps that moving vehicle information acquired by an image acquisition device is sent to a server through communication equipment, the server at a background extracts and tracks a target vehicle through an image processing algorithm, the position of the vehicle is acquired through geometric relation operation, and then the position of a user vehicle is sent to a vehicle user terminal; meanwhile, the server also pushes parking space information, empty parking space information selected by the user and navigation information from the position of the vehicle of the user to the position of the empty parking space selected by the user to the user, so that the real-time positioning and navigation of the vehicle in the parking lot are realized;
the image acquisition device consists of a plurality of cameras, and each camera is fixed and has a certain downward inclination angle;
in the server, the target vehicle is extracted and tracked through an image processing algorithm as follows:
(1) Modeling a Gaussian mixture model, namely, modeling each pixel by using K Gaussian distributions to form the Gaussian mixture model by calculating the average gray value and the pixel variance of each pixel in a video sequence image acquired by an image acquisition device in a period of time, wherein the K value is 3-5;
(2) Updating the model, namely matching each pixel of the image frame with K Gaussian distributions in the mixed Gaussian model at the moment t, and keeping the mean value and covariance matrix of unmatched Gaussian distributions unchanged; the matched Gaussian distribution needs to update the parameters of each Gaussian distribution and the weight of each Gaussian distribution, the Gaussian distributions are sorted according to the weight, and new Gaussian distributions are added for model updating;
(3) Foreground detection, namely performing descending order sorting on K Gaussian distributions of each pixel by using the ratio of the weight and the standard deviation obtained in the step (2), wherein the Gaussian distribution which is most likely to describe the stable background process is positioned in front of the sequence, the first B Gaussian distributions are taken as background models, each pixel value at the current moment is matched with the first B Gaussian distributions, matching exists, and the pixel point is a background point; otherwise, the pixel is detected as a moving target, namely a moving vehicle;
(4) And (4) tracking and positioning the target vehicle, taking the foreground obtained in the step (3) as initial target vehicle information, and combining a Camshift algorithm and a Kalman filter algorithm to realize accurate identification and positioning of the moving vehicle at the subsequent moment so as to finish tracking and positioning of the target vehicle.
2. The video image processing-based indoor vehicle positioning and navigation system according to claim 1, wherein: in the server, the calculation process of obtaining the position coordinates of the vehicle through geometric relation calculation is as follows:
(1) Calculating a maximum included angle alpha and a minimum included angle beta between a vertical visual angle of the camera and a y axis of a ground plane and an included angle gamma between the projection of a horizontal visual angle of the camera at the horizontal visual angle and the y axis of the ground plane according to the camera pin hole model, the camera position, the installation angle and the acquired basic parameters of the video image;
α＝arctan(H/y 1 )
β＝arctan(H/(y 1 +y 2 ))
γ＝acrtan(x 1 /y 1 )
(2) Determining the actual coordinates P (x, y) of the target in the image according to the calculation result in the step (1), wherein x and y respectively represent the coordinate position of the moving target in the parking lot,
3. the video image processing-based indoor vehicle positioning and navigation system according to claim 1, wherein: the vehicle user terminal is a mobile phone, a vehicle-mounted terminal and a platform computer.
4. The video image processing-based indoor vehicle positioning and navigation system according to claim 1, wherein: the communication equipment is wireless communication equipment and is arranged in the user terminal.
5. An indoor vehicle positioning and navigation method based on video image processing of the indoor vehicle positioning and navigation system according to claim 1, characterized by the following: cameras are arranged at a plurality of places of the indoor parking, are used for capturing moving vehicles and transmit image data to a server of a background in real time by utilizing the cameras; an electronic map of an indoor parking lot is arranged in the vehicle-mounted user terminal, position information of a camera is arranged in the electronic map and can be also marked on a background server, moving vehicle information acquired by the camera is sent to the background server, the server extracts and tracks a target vehicle through an image processing algorithm, the vehicle position is acquired through geometric relation operation, and the position of the user vehicle is sent to the vehicle user terminal; meanwhile, the server also pushes parking space information and empty parking space information selected by the user to the user, and navigation information from the vehicle position of the user to the empty parking space position selected by the user, so that real-time positioning and navigation of the vehicle in the parking lot are realized.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611019433.7A CN107067794B (en) | 2016-11-18 | 2016-11-18 | Indoor vehicle positioning and navigation system and method based on video image processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611019433.7A CN107067794B (en) | 2016-11-18 | 2016-11-18 | Indoor vehicle positioning and navigation system and method based on video image processing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107067794A CN107067794A (en) | 2017-08-18 |
| CN107067794B true CN107067794B (en) | 2023-04-18 |
Family
ID=59619071
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611019433.7A Active CN107067794B (en) | 2016-11-18 | 2016-11-18 | Indoor vehicle positioning and navigation system and method based on video image processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107067794B (en) |
Families Citing this family (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107990873B (en) * | 2017-09-22 | 2020-04-17 | 东莞市光劲光电有限公司 | Mode for positioning by using LED intelligent lamp |
| CN107888877B (en) * | 2017-11-13 | 2020-10-09 | 深圳市戴升智能科技有限公司 | Method and system for vehicle tracking and road traffic information acquisition |
| CN107958611A (en) * | 2017-12-25 | 2018-04-24 | 北京无线电计量测试研究所 | A kind of intelligent interconnection shutdown system based on image recognition indoor positioning |
| CN110162028A (en) * | 2018-02-11 | 2019-08-23 | 北京图森未来科技有限公司 | A kind of vehicle location shutdown system, method and apparatus |
| CN108417047A (en) * | 2018-05-10 | 2018-08-17 | 杭州盈蝶科技有限公司 | A kind of vehicle location method for tracing and its system |
| CN108847053A (en) * | 2018-08-28 | 2018-11-20 | 龙荟智能科技（上海）有限责任公司 | A kind of indoor navigation method |
| CN109051321A (en) * | 2018-09-14 | 2018-12-21 | 山东上拓教育咨询有限公司 | A kind of fresh commodities circulating cases of the low temperature that intelligence follows automatically |
| CN109448438A (en) * | 2018-12-03 | 2019-03-08 | 郑州云海信息技术有限公司 | A kind of garage parking traffic control method, device, terminal and storage medium |
| CN109895684A (en) * | 2019-04-03 | 2019-06-18 | 武汉理工大学 | A kind of vehicle driving early warning system and method based on image monocular vision |
| CN110264777B (en) * | 2019-06-26 | 2020-12-15 | 广州小鹏汽车科技有限公司 | Indoor vehicle navigation method and device, storage medium and vehicle control terminal |
| CN110223534A (en) * | 2019-06-28 | 2019-09-10 | 信利光电股份有限公司 | A kind of parking lot automatic navigation method and system |
| CN110390836A (en) * | 2019-07-17 | 2019-10-29 | 青岛海尔空调器有限总公司 | For guiding the method, apparatus and managing system of car parking of travel route |
| CN110473256A (en) * | 2019-07-18 | 2019-11-19 | 中国第一汽车股份有限公司 | A kind of vehicle positioning method and system |
| CN110503850A (en) * | 2019-07-19 | 2019-11-26 | 青岛海尔空调器有限总公司 | Method, apparatus and vehicle management system for vehicle management |
| CN110980084A (en) * | 2019-12-13 | 2020-04-10 | 灵动科技（北京）有限公司 | Warehousing system and related method |
| CN112284396B (en) * | 2020-10-29 | 2023-01-03 | 的卢技术有限公司 | Vehicle positioning method suitable for underground parking lot |
| CN113470098B (en) * | 2021-06-02 | 2022-04-01 | 合肥泰瑞数创科技有限公司 | Parking lot real-time three-dimensional model establishing method and system and storage medium |
| CN115731736A (en) * | 2022-12-03 | 2023-03-03 | 中邮科通信技术股份有限公司 | System and method for realizing indoor parking positioning navigation based on AI vision technology |
| CN116137109B (en) * | 2023-04-17 | 2023-07-07 | 青岛益合泊朗创新科技有限公司 | Mechanical parking equipment control system and method based on cloud computing |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103606301A (en) * | 2013-11-27 | 2014-02-26 | 南通芯迎设计服务有限公司 | Parking and vehicle locating method based on intelligent terminal |
| WO2015014018A1 (en) * | 2013-08-01 | 2015-02-05 | Mao Weiqing | Indoor positioning and navigation method for mobile terminal based on image recognition technology |
-
2016
- 2016-11-18 CN CN201611019433.7A patent/CN107067794B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015014018A1 (en) * | 2013-08-01 | 2015-02-05 | Mao Weiqing | Indoor positioning and navigation method for mobile terminal based on image recognition technology |
| CN103606301A (en) * | 2013-11-27 | 2014-02-26 | 南通芯迎设计服务有限公司 | Parking and vehicle locating method based on intelligent terminal |
Non-Patent Citations (1)
| Title |
|---|
| 蔡胜利 ; 张会清 ; .基于序列图像块匹配的室内定位算法研究.计算机测量与控制.2010,(07),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107067794A (en) | 2017-08-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107067794B (en) | Indoor vehicle positioning and navigation system and method based on video image processing | |
| US20210003684A1 (en) | Online sensor calibration for autonomous vehicles | |
| US9996936B2 (en) | Predictor-corrector based pose detection | |
| WO2020055928A1 (en) | Calibration for vision in navigation systems | |
| CN108810473B (en) | Method and system for realizing GPS mapping camera picture coordinate on mobile platform | |
| KR101663669B1 (en) | Spatial predictive approximation and radial convolution | |
| CN111444845B (en) | Non-motor vehicle illegal stop recognition method, device and system | |
| CN109345599B (en) | Method and system for converting ground coordinates and PTZ camera coordinates | |
| US11290705B2 (en) | Rendering augmented reality with occlusion | |
| US20220044558A1 (en) | Method and device for generating a digital representation of traffic on a road | |
| US10817747B2 (en) | Homography through satellite image matching | |
| CN106370160A (en) | Robot indoor positioning system and method | |
| US20200082565A1 (en) | Calibration for Vision in Navigation Systems | |
| WO2020211593A1 (en) | Digital reconstruction method, apparatus, and system for traffic road | |
| CN107301658B (en) | Method for fast matching and positioning unmanned aerial vehicle image and large-scale old time phase image | |
| CN111177297B (en) | Dynamic target speed calculation optimization method based on video and GIS | |
| CN207068261U (en) | A kind of indoor vehicle Position Fixing Navigation System based on Computer Vision | |
| CN115373416B (en) | Intelligent inspection method for railway electric power through line | |
| KR100981588B1 (en) | A system for generating geographical information of city facilities based on vector transformation which uses magnitude and direction information of feature point | |
| CN113011445A (en) | Calibration method, identification method, device and equipment | |
| Wu et al. | A method of information fusion for the civil aviation ASTERIX data and airport surface video surveillance | |
| CN114973147A (en) | Distributed monitoring camera positioning method and system based on laser radar mapping | |
| CN111899512B (en) | Vehicle track extraction method and system combined with skyline observation and storage medium | |
| CN110909648A (en) | People flow monitoring method implemented on edge computing equipment by using neural network | |
| CN113112544B (en) | Personnel positioning abnormity detection system based on intelligent Internet of things and big data |
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 |