CN108801257B - Positioning method for indoor automatic parking - Google Patents
Positioning method for indoor automatic parking Download PDFInfo
- Publication number
- CN108801257B CN108801257B CN201810297034.XA CN201810297034A CN108801257B CN 108801257 B CN108801257 B CN 108801257B CN 201810297034 A CN201810297034 A CN 201810297034A CN 108801257 B CN108801257 B CN 108801257B
- Authority
- CN
- China
- Prior art keywords
- binary
- bit
- information
- grid
- grids
- 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
- 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
Abstract
The invention discloses a positioning method for indoor automatic parking, which comprises the following steps: (1) spraying grids on the roads of the indoor parking lot, wherein the grids are coded by binary systems; (2) inputting the binary digit sequence corresponding to the actual position into a GIS database; (3) the camera shoots the picture of the grid on the ground and uploads the picture to the server; (4) identifying the grid information and reading out a binary digit sequence; (5) and inquiring the actual position of the vehicle in a GIS database according to the output binary digit sequence. The invention combines the technologies of computer vision, position coding, position service and the like, stores the position data into the database, obtains binary ID information by identifying the drawn grids, is convenient to use, has higher positioning precision, can accurately and reliably position the vehicle indoors, and has wide application range.
Description
Technical Field
The invention relates to a vehicle parking method, in particular to a positioning method for indoor automatic parking. .
Background
With the continuous progress of scientific technology, indoor positioning technology is continuously developed, and bluetooth indoor positioning technology, infrared indoor positioning technology, ultra wide band indoor positioning technology, Zigbee indoor positioning technology, WiFi indoor positioning technology and the like are available. However, these techniques are inconvenient to use and cannot meet the positioning requirements of automatic parking. Therefore, a stable and high-precision positioning method which is convenient to use is urgently needed for indoor automatic parking.
Disclosure of Invention
The purpose of the invention is as follows: aiming at the problems in the prior art, the invention aims to provide a positioning method for indoor automatic parking, which is convenient to use and high in positioning precision.
The technical scheme is as follows: a positioning method for indoor automatic parking comprises the following steps:
(1) spraying grids on the roads of the indoor parking lot, wherein the grids are coded by binary systems;
(2) inputting the binary digit sequence corresponding to the actual position into a GIS database;
(3) the camera shoots the picture of the grid on the ground and uploads the picture to the server;
(4) identifying the grid information and reading out a binary digit sequence;
(5) and inquiring the actual position of the vehicle in a GIS database according to the output binary digit sequence.
The step (1) comprises the following steps:
(1.1) using n-bit binary coding, the main part has n grids, one grid is a meter x a meter, the road width can be represented as n x a m, and the road length can be represented as 2n*a=2na meters, representable area na 2na=n2na2Square meter;
(1.2) spraying black and white on the grid, wherein black represents a binary digit 1, and white represents a binary digit 0;
(1.3) setting a start bit, a stop bit and a check bit; the start bit is black and set as '1', and the end bit is white and set as '0'; odd or even check bits are adopted, so that the number of '1' between the start bit and the end bit is always an odd number or an even number;
(1.4) sequentially encoding, the ID information of each road section from the beginning to the end is continuous.
The step (2) comprises the following steps:
in the GIS database, a straight line segment is represented by its type and binary ID information at its two ends and their actual coordinates: { S; ID1, (X1, Y1); ID2, (X2, Y2); the circular arc road section is represented by the type, the angle, the center coordinate, the binary ID information of two ends and the actual coordinates of the two binary ID information: { C; theta; (X0, Y0); ID1, (X1, Y1); ID2, (X2, Y2).
The step (4) comprises the following steps:
(4.1) carrying out gray processing on the color grid image shot by the camera, reducing the data volume and reducing the storage space and the image processing time;
(4.2) removing noise points introduced when the grid image is shot by using median filtering, and reducing the interference of noise on subsequent image processing;
(4.3) carrying out binarization on the image, and carrying out binarization on the grid image by adopting an algorithm combining self-adaptive illumination balance and an Otsu global threshold value to remove the influence of uneven illumination of the grid image;
(4.4) extracting edge features, and calculating the total length L, wherein the coordinates of the ith sampling point are (Li/(n +3), a/2), and i < ═ n + 3;
(4.5) sampling points according to the obtained coordinates, wherein the dark color is marked as '0' and the light color is marked as '1';
(4.6) outputting a binary codeword from the start bit to the end bit; the first sampling point and the last sampling point are necessarily one "0" and one "1" regardless of whether the vehicle is driving forward or backward; if the '1' is at the left end, outputting a binary code word from left to right, and removing the start bit, the end bit and the check bit after checking to obtain ID information; if '1' is at the right end, the binary code word is output from right to left, and the start bit, the end bit and the check bit are removed after checking to obtain ID information.
The step (5) comprises the following steps:
(5.1) searching which link between the two end IDs of the link the ID is between according to the detected binary ID information, and then the actual position is on the link;
(5.2) according to the searched data of the actual road section, if the data is { S; ID1, (X1, Y1); ID2, (X2, Y2) }, namely, the road section is linear, the (ID-ID1) is converted into a decimal number A, the (ID2-ID1) is converted into a decimal number B, and the current actual coordinates are (A (X2-X1)/B, and A (Y2-Y1)/B); if the road section data is { C; theta; (X0, Y0); ID1, (X1, Y1); ID2, (X2, Y2) }, then the radius of the circular arc R ═ v √ (X0-X1)2+(Y0-Y1)2Then the current actual coordinate is
Advantageous effects
Compared with the prior art, the invention has the following remarkable progress: the invention combines the technologies of computer vision, position coding, position service and the like, stores the position data into the database, obtains binary ID information by identifying the drawn grids, is convenient to use, has higher positioning precision, can accurately and reliably position the vehicle indoors, and has wide application range.
Drawings
FIG. 1 is a schematic flow diagram of a construction method according to the present invention;
FIG. 2 is a schematic view of a grid of straight line segments;
FIG. 3 is a schematic view of a circle segment;
fig. 4 is a schematic diagram of calculating sampling points.
Detailed Description
The technical solution of the present invention will be further described in detail with reference to the following embodiments and the accompanying drawings.
As shown in fig. 1, a positioning method for indoor automatic parking includes the following steps:
firstly, spraying grids on the road of the indoor parking lot, wherein the grids are coded by binary systems. By using 32-bit binary coding, the body part has 32 grids, and one grid is 25cm × 25cm, so that the road width can be represented as 32 × 0.25 ═ 8 m, and the road length can be represented as 232*0.25=230Rice, representable area 8 x230=233Square meter, about 8590 square kilometers. The grid is painted with black and white, where black represents the binary number 1 and white represents the binary number 0. Setting a start bit, an end bit and a check bit. The start bit is black and set to "1", and the end bit is white and set to "0". And (3) adopting even check bits to ensure that the number of '1' between the start bit and the end bit is always an even number. And sequentially encoding, wherein the ID information of each road section is continuous from beginning to end.
And step two, recording the binary digit sequence corresponding to the actual position into a GIS database. In the GIS database, a straight line segment is represented by its type and binary ID information at its two ends, as well as their actual coordinates. In this example, the straight line segment is represented as { S; ID1, (X1, Y1); ID2, (X2, Y2); the circular arc segment is represented by its type, center coordinates, angle, and binary ID information of both ends and their actual coordinates. In this example, the circular arc segment is represented as { C; theta; (X0, Y0); ID1, (X1, Y1); ID2, (X2, Y2).
Step three, when the vehicle drives into the indoor parking lot, the vehicle-mounted camera shoots the picture of the grid on the ground and uploads the picture to the server;
and step four, identifying the grid information and reading out the binary digit sequence. The color of each pixel in the color image is determined by R, G, B three components, and each component has 255 values, so that a pixel can have a color variation range of 1600 tens of thousands (255 x 255). The variation range of one pixel point of the gray image is only 255, but the description of the gray image still reflects the distribution and the characteristics of the whole and local chromaticity and brightness levels of the whole image like the color image. The gray processing is carried out on the color grid image shot by the camera, so that the data volume is reduced, and the storage space and the image processing time are reduced. Odd numbers are taken out from a certain sampling window in the image and are arranged in an ascending or descending order, the values of all the points after the ordering are subjected to arithmetic mean calculation, the calculated median value replaces the value to be processed, the surrounding pixel values are close to the real values, the median filtering of the image is realized, the noise points introduced when the grid image is shot are removed, and the interference of the noise on the subsequent image processing is reduced. And carrying out binarization on the image, and carrying out binarization on the grid image by adopting an algorithm combining self-adaptive illumination balance and an Otsu global threshold value to remove the influence of uneven illumination of the grid image. Wherein the process of the Otsu algorithm is as follows. Let the image contain L gray levels (0,1 …, L-1), the number of pixel points for a gray value i is Ni, and the total number of pixel points of the image is N0+ N1+. + N (L-1). The summary of the points with gray value i is: p (i) ═ n (i)/n. threshold t divides the whole image into two classes, dark c1 and bright c2, then the between-class variance σ is a function of t: σ -a 1-a 2(u1-u2) ^2(2) where aj is the ratio of cj-like area to total image area, a 1-sum (P (i)) i- > t, a 2-1-a 1; uj is the mean value of class cj, u1 ═ sum (i × p (i))/a 10- > t, u2 ═ sum (i × p (i))/a2, t +1- > L-1. the method selects the optimal threshold t ^ to maximize the inter-class variance, namely: let Δ u be u1-u2, σ b be max { a1(t) × a2(t) Δ u ^2 }. And extracting edge features of the image, extracting grids from the whole image, and calculating the total length L of the grids, wherein the coordinates of the ith sampling point are (0.25/2, Li/34). And sampling the binarized grid image according to the coordinates of the obtained sampling points, wherein the dark color is marked as '0' and the light color is marked as '1'. A binary codeword is output from the start bit to the end bit. Regardless of whether the vehicle is driving forward or backward, the first and last sampling points must be "0" and "1" respectively. If the '1' is at the left end, outputting a binary code word from left to right, and removing the start bit, the end bit and the check bit after checking to obtain ID information; if '1' is at the right end, the binary code word is output from right to left, and the start bit, the end bit and the check bit are removed after checking to obtain ID information.
And step five, inquiring the actual position of the vehicle in a GIS database according to the output binary digit sequence. And searching which link the ID is between the two end IDs according to the detected binary ID information, and then the actual position is on the link. In this example, assuming that the detected ID is (01000000000000000000000000000000), if the data of the searched actual link is { S; ID1, (X1, Y1); ID2, (X2, Y2) }, namely, the road section is linear, the (ID-ID1) is converted into the decimal number 2, the (ID2-ID1) is converted into the decimal number 11, and then the current actual coordinates are (2(X2-X1)/11, and 2 (Y2-Y1)/11); if the road section data is { C; theta; (X0, Y0); ID1, (X1, Y1); ID2, (X2, Y2) }, i.e. the road section is circular arc, making the radius of the circular arc R √ (X0-X1)2+(Y0-Y1)2Then the current actual coordinate is
Claims (1)
1. A positioning method for indoor automatic parking is characterized by comprising the following steps:
(1) spraying grids on the roads of the indoor parking lot, wherein the grids are coded by binary systems; the method specifically comprises the following steps:
(1.1) using n-bit binary coding, the main part has n grids, one grid has the sizea m x a m, the road width is n x a n m, and the road length is 2n*a=2na m, area na 2na=n2na2Square meter;
(1.2) spraying black and white on the grid, wherein black represents a binary digit 1, and white represents a binary digit 0;
(1.3) setting a start bit, a stop bit and a check bit; the start bit is black and set as '1', and the end bit is white and set as '0'; odd or even check bits are adopted, so that the number of '1' between the start bit and the end bit is always an odd number or an even number;
(1.4) sequentially encoding, wherein the ID information of each road section from beginning to end is continuous;
(2) inputting the binary digit sequence corresponding to the actual position into a GIS database; the method specifically comprises the following steps:
in the GIS database, a straight line segment is represented by its type and binary ID information at its two ends and their actual coordinates: { S; ID1, (X1, Y1); ID2, (X2, Y2); the circular arc road section is represented by the type, the angle, the center coordinate, the binary ID information of two ends and the actual coordinates of the two binary ID information: { C; theta; (X0, Y0); ID1, (X1, Y1); ID2, (X2, Y2);
(3) the camera shoots the picture of the grid on the ground and uploads the picture to the server;
(4) identifying the grid information and reading out a binary digit sequence; the method specifically comprises the following steps:
(4.1) carrying out gray processing on the color grid image shot by the camera, reducing the data volume and reducing the storage space and the image processing time;
(4.2) removing noise points introduced when the grid image is shot by using median filtering, and reducing the interference of noise on subsequent image processing;
(4.3) carrying out binarization on the image, and carrying out binarization on the grid image by adopting an algorithm combining self-adaptive illumination balance and an Otsu global threshold value to remove the influence of uneven illumination of the grid image;
(4.4) extracting edge features, and calculating the total length L, wherein the coordinates of the ith sampling point are (Li/(n +3), a/2), and i < ═ n + 3;
(4.5) sampling points according to the obtained coordinates, wherein the dark color is marked as '0' and the light color is marked as '1';
(4.6) outputting a binary codeword from the start bit to the end bit; the first sampling point and the last sampling point are necessarily one "0" and one "1" regardless of whether the vehicle is driving forward or backward; if the '1' is at the left end, outputting a binary code word from left to right, and removing the start bit, the end bit and the check bit after checking to obtain ID information; if the '1' is at the right end, outputting a binary code word from right to left, and after checking, omitting an initial bit, a termination bit and a check bit to obtain ID information;
(5) inquiring the actual position of the vehicle in a GIS database according to the output binary digit sequence; the method specifically comprises the following steps:
(5.1) searching which link between the two end IDs of the link the ID is between according to the detected binary ID information, and then the actual position is on the link;
(5.2) according to the searched data of the actual road section, if the data is { S; ID1, (X1, Y1); ID2, (X2, Y2) }, namely, the road section is linear, the (ID-ID1) is converted into a decimal number A, the (ID2-ID1) is converted into a decimal number B, and the current actual coordinates are (A (X2-X1)/B, and A (Y2-Y1)/B); if the road section data is { C; theta; (X0, Y0); ID1, (X1, Y1); ID2, (X2, Y2) }, the radius of the circular arcThen the current actual coordinates are
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810297034.XA CN108801257B (en) | 2018-04-04 | 2018-04-04 | Positioning method for indoor automatic parking |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810297034.XA CN108801257B (en) | 2018-04-04 | 2018-04-04 | Positioning method for indoor automatic parking |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108801257A CN108801257A (en) | 2018-11-13 |
CN108801257B true CN108801257B (en) | 2021-05-11 |
Family
ID=64094843
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810297034.XA Active CN108801257B (en) | 2018-04-04 | 2018-04-04 | Positioning method for indoor automatic parking |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108801257B (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109532824B (en) * | 2018-12-19 | 2020-09-01 | 杭州湘滨电子科技有限公司 | Road edge identification method for horizontal parking |
CN111161449A (en) * | 2020-01-07 | 2020-05-15 | 东南大学 | Vehicle large-scale parking lot interior positioning method based on automobile data recorder image |
CN113435227B (en) * | 2020-03-23 | 2023-04-07 | 阿里巴巴集团控股有限公司 | Map generation and vehicle positioning method, system, device and storage medium |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1996289A (en) * | 2006-12-26 | 2007-07-11 | 董崇军 | Searching and positioning method using electronic map |
CN102479214A (en) * | 2010-11-30 | 2012-05-30 | 余政 | Positioning method and positioning system based on bar code identification technology and GIS (Geographic Information System) technology |
CN103292805A (en) * | 2013-05-28 | 2013-09-11 | 武汉理工大学 | Indoor navigation system and indoor navigation method thereof |
CN104457738A (en) * | 2014-11-11 | 2015-03-25 | 龚斌 | Indoor navigation method based on mobile terminal application |
CN104596525A (en) * | 2014-12-29 | 2015-05-06 | 西南交通大学 | Vehicle positioning method based on coded graphics |
CN106169247A (en) * | 2016-08-04 | 2016-11-30 | 上海交通大学 | The garage parking indoor positioning of view-based access control model and map and micro navigation system and method |
CN106197417A (en) * | 2016-06-22 | 2016-12-07 | 平安科技(深圳)有限公司 | The indoor navigation method of handheld terminal and handheld terminal |
CN106468553A (en) * | 2016-08-30 | 2017-03-01 | 上海擎朗智能科技有限公司 | A kind of localization method of the mobile object based on road sign |
CN107301787A (en) * | 2017-07-28 | 2017-10-27 | 东南大学 | Large parking lot positioning and bootstrap technique based on position Quick Response Code |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6606554B2 (en) * | 2001-09-27 | 2003-08-12 | Siemens Information & Communication Mobile Llc | Method and apparatus for defining location coordinates |
US7551083B2 (en) * | 2004-10-20 | 2009-06-23 | Jerold Russell Modes | Systems, methods and devices for area-based localization |
-
2018
- 2018-04-04 CN CN201810297034.XA patent/CN108801257B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1996289A (en) * | 2006-12-26 | 2007-07-11 | 董崇军 | Searching and positioning method using electronic map |
CN102479214A (en) * | 2010-11-30 | 2012-05-30 | 余政 | Positioning method and positioning system based on bar code identification technology and GIS (Geographic Information System) technology |
CN103292805A (en) * | 2013-05-28 | 2013-09-11 | 武汉理工大学 | Indoor navigation system and indoor navigation method thereof |
CN104457738A (en) * | 2014-11-11 | 2015-03-25 | 龚斌 | Indoor navigation method based on mobile terminal application |
CN104596525A (en) * | 2014-12-29 | 2015-05-06 | 西南交通大学 | Vehicle positioning method based on coded graphics |
CN106197417A (en) * | 2016-06-22 | 2016-12-07 | 平安科技(深圳)有限公司 | The indoor navigation method of handheld terminal and handheld terminal |
CN106169247A (en) * | 2016-08-04 | 2016-11-30 | 上海交通大学 | The garage parking indoor positioning of view-based access control model and map and micro navigation system and method |
CN106468553A (en) * | 2016-08-30 | 2017-03-01 | 上海擎朗智能科技有限公司 | A kind of localization method of the mobile object based on road sign |
CN107301787A (en) * | 2017-07-28 | 2017-10-27 | 东南大学 | Large parking lot positioning and bootstrap technique based on position Quick Response Code |
Non-Patent Citations (1)
Title |
---|
基于RFID/GIS/GPS的物流商品监控系统模型研究;胡立栓等;《测绘与空间地理信息》;20130825;第128-132页 * |
Also Published As
Publication number | Publication date |
---|---|
CN108801257A (en) | 2018-11-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108801257B (en) | Positioning method for indoor automatic parking | |
CN111079649B (en) | Remote sensing image ground feature classification method based on lightweight semantic segmentation network | |
US20180300549A1 (en) | Road detecting method and apparatus | |
CN109285198B (en) | Method for coding and identifying annular coding mark points | |
CN107909638B (en) | Rendering method, medium, system and electronic device of virtual object | |
CN104243820A (en) | Method and device for determining boundary of image | |
CN112949633B (en) | Improved YOLOv 3-based infrared target detection method | |
CN111145255A (en) | Pose calculation method and system combining deep learning and geometric optimization | |
CN105678318A (en) | Traffic label matching method and apparatus | |
CN110992366A (en) | Image semantic segmentation method and device and storage medium | |
CN111488821B (en) | Method and device for identifying countdown information of traffic signal lamp | |
US9396552B1 (en) | Image change detection | |
US11609332B2 (en) | Method and apparatus for generating image using LiDAR | |
EP4174792A1 (en) | Method for scene understanding and semantic analysis of objects | |
Rawashdeh et al. | Camera–Lidar sensor fusion for drivable area detection in winter weather using convolutional neural networks | |
CN104268513A (en) | Method and device for acquiring road guide data | |
CN111310772B (en) | Point line characteristic selection method and system for binocular vision SLAM | |
CN111505577A (en) | Mobile vehicle positioning method based on visible light communication | |
CN106403962B (en) | The coding of position mark | |
CN113345101B (en) | Three-dimensional point cloud labeling method, device, equipment and storage medium | |
CN111612836B (en) | Identification method and system for hollow circular pointer type instrument | |
CN115018926A (en) | Method, device and equipment for determining pitch angle of vehicle-mounted camera and storage medium | |
CN115773744A (en) | Model training and road network processing method, device, equipment, medium and product | |
CN111401377B (en) | Meter data reading method and device, electronic equipment and storage medium | |
CN111353441B (en) | Road extraction method and system based on position data fusion |
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 |