CN111881824B - Indoor map acquisition method and system based on image recognition - Google Patents
Indoor map acquisition method and system based on image recognition Download PDFInfo
- Publication number
- CN111881824B CN111881824B CN202010737066.4A CN202010737066A CN111881824B CN 111881824 B CN111881824 B CN 111881824B CN 202010737066 A CN202010737066 A CN 202010737066A CN 111881824 B CN111881824 B CN 111881824B
- Authority
- CN
- China
- Prior art keywords
- specific image
- image
- map
- shooting
- 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
- 238000000034 method Methods 0.000 title claims abstract description 18
- 238000012545 processing Methods 0.000 claims description 18
- 238000007781 pre-processing Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 5
- 238000004422 calculation algorithm Methods 0.000 claims description 4
- 238000004519 manufacturing process Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 abstract description 4
- 238000005516 engineering process Methods 0.000 abstract description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
-
- 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
- G01C21/005—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 with correlation of navigation data from several sources, e.g. map or contour matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Multimedia (AREA)
- Automation & Control Theory (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Processing Or Creating Images (AREA)
- Image Processing (AREA)
Abstract
The invention discloses an indoor map acquisition method and system based on image recognition, wherein the method comprises the following steps: acquiring scene images shot by a camera at different indoor shooting positions aiming at indoor specific image identifications, and identifying target shapes of the specific image identifications in the scene images; calculating the path distance between corresponding shooting positions or the path distance between the shooting positions and the corresponding specific image mark based on the target shape of the specific image mark in the scene image; and taking the path distance as a unit, and automatically generating all map primitive data in a system. The invention can automatically record the road junction path data information through the computer image recognition technology based on the condition of low accuracy requirement of the indoor map, does not need manual point-by-point and line-by-line mapping and manual drawing editing, and has small workload and high reliability.
Description
Technical Field
The invention relates to the technical field of map acquisition, in particular to an indoor map acquisition method and system based on image recognition.
Background
At present, a professional surveying instrument is generally adopted for indoor map acquisition, and a path cannot be automatically recorded through a driving track because the indoor map acquisition does not have GPS positioning conditions.
Therefore, the current indoor map acquisition is mainly performed through manual point-by-point and line-by-line mapping and recording, the workload is very large, and errors are easy to occur.
Disclosure of Invention
Therefore, the embodiment of the invention provides an indoor map acquisition method and system based on image recognition, which are used for solving the problems in the prior art.
In order to achieve the above object, the embodiments of the present invention provide the following technical solutions:
the invention provides an indoor map acquisition method based on image recognition, which comprises the following steps:
acquiring scene images shot by a camera at different indoor shooting positions aiming at indoor specific image identifications, and identifying target shapes of the specific image identifications in the scene images;
Calculating the path distance between corresponding shooting positions or the path distance between the shooting positions and the corresponding specific image mark based on the target shape of the specific image mark in the scene image;
And taking the path distance as a unit, and automatically generating all map primitive data in a system.
Optionally, the map primitive data is a distance between all adjacent two shooting positions, or a distance between all shooting positions and the specific image identifier.
Optionally, the acquiring the scene image captured by the camera for the indoor specific image identification at different indoor capturing positions further includes a preprocessing step, including:
Manually manufacturing the specific image mark in advance, and calibrating a camera;
The pretreatment step is a step of manual pretreatment.
Optionally, the preprocessing step further includes: and forming roads with a plurality of intersections in a room, fixing a specific image identifier at one end of the roads in the room, and shooting the scene images at the different intersections on the roads to obtain the map primitive data, wherein the map primitive data are the distances from all shooting positions to the specific image identifier.
Optionally, the preprocessing step further includes: and when the scene image is shot, respectively fixing the specific image mark and the shooting position at any two adjacent intersections, wherein the map primitive data are the distances between all the two adjacent shooting positions.
Optionally, the step calculates a path distance between corresponding shooting positions based on the target shape of the specific image identifier in the scene image, or the path distance between the shooting position and the corresponding specific image identifier, and all acquired scene images are imported into a computer for automatic identification and recognition, and the path distance is calculated according to an image algorithm.
Optionally, the map primitive data automatically generates intersection and road layer data through a computer program according to the azimuth data and the distance data to complete the map;
And the specific image mark is a plastic plate with the thickness of 60cm and 60cm, black and white square pictures are posted on the surface of the plastic plate, squares are 3*3, and each small square is 20cm and 20cm.
Optionally, the step calculates a path distance between corresponding shooting positions or a path distance between a shooting position and a corresponding specific image identifier based on the target shape of the specific image identifier in the scene image, and further includes an image preprocessing step, including:
Performing enhancement processing and noise reduction processing on the scene image;
After the image preprocessing step, if the computer cannot identify the specific image identifier, reminding and displaying a re-shooting mark.
The invention also provides an indoor map acquisition device based on image recognition, which comprises:
The acquisition unit is used for acquiring scene images shot by the camera at different indoor shooting positions aiming at indoor specific image identifications and identifying target shapes of the specific image identifications in the scene images;
A processing unit, configured to calculate a path distance between corresponding shooting positions, or a path distance between a shooting position and a corresponding specific image identifier, based on a target shape of the specific image identifier in the scene image;
And the execution unit is used for taking the path distance as a unit and automatically generating all map primitive data in the system.
Optionally, the method further comprises:
an image processing unit configured to:
Performing enhancement processing and noise reduction processing on the scene image;
after the image preprocessing, if the computer cannot identify the specific image identification, reminding and displaying the re-shooting mark.
The invention has the following advantages:
The invention can automatically record the road junction path data information through the computer image recognition technology based on the condition of low accuracy requirement of the indoor map, does not need manual point-by-point and line-by-line mapping and manual drawing editing, and has small workload and high reliability.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It will be apparent to those of ordinary skill in the art that the drawings in the following description are exemplary only and that other implementations can be obtained from the extensions of the drawings provided without inventive effort.
FIG. 1 is a flow chart of a method provided by the invention.
Detailed Description
Other advantages and advantages of the present invention will become apparent to those skilled in the art from the following detailed description, which, by way of illustration, is to be read in connection with certain specific embodiments, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
As shown in fig. 1, the invention provides an indoor map acquisition method based on image recognition, which comprises the following steps:
Step 100, manually preprocessing, namely firstly manufacturing the specific image mark and calibrating a camera;
Based on a computer, acquiring scene images shot by a camera at different indoor shooting positions aiming at indoor specific image identifications, and identifying target shapes of the specific image identifications in the scene images;
Step 200, calculating a path distance between corresponding shooting positions or a path distance between the shooting positions and the corresponding specific image mark based on the target shape of the specific image mark in the scene image; all acquired scene images are imported into a computer for automatic identification and recognition, and the path distance is calculated according to an image algorithm;
Step 300, taking the path distance as a unit, and automatically generating all map primitive data in a system; the map primitive data automatically generates crossing and road layer data according to the azimuth data and the distance data through a computer program to complete the map.
Wherein the system is a computer system; the specific image is marked as a plastic plate with 60cm by 60cm, black and white square pictures are posted on the surface of the plastic plate, squares are 3*3, and each square is 20cm by 20cm.
The map primitive data are distances between all adjacent two shooting positions or distances between all the shooting positions and the specific image mark. The following description is given with two primitive data types:
first kind: the map primitive data is the distance between all adjacent two shooting positions.
And when the scene image is shot, respectively fixing the specific image mark and the shooting position at any two adjacent intersections, wherein the map primitive data are the distances between all the two adjacent shooting positions.
Second, the map primitive data is the distance from all shooting positions to the specific image identifier.
And forming roads with a plurality of intersections in a room, fixing a specific image identifier at one end of the roads in the room, and shooting the scene images at the different intersections on the roads to obtain the map primitive data, wherein the map primitive data are the distances from all shooting positions to the specific image identifier.
Step 200 further includes an image preprocessing step, in which enhancement processing and noise reduction processing are performed on the scene image; after the image preprocessing step, if the computer cannot identify the specific image identifier, reminding and displaying a re-shooting mark.
One specific embodiment of the invention is provided below:
Firstly, specific image identifications are manufactured, cameras are calibrated to improve measurement accuracy, a site acquisition map is completed by two persons together, A holds the cameras to stand at one intersection, B holds the identification plates to stand at the next intersection, the two intersections are in a communication relationship (passable), B holds the identification plates to be vertical to the ground and right against the cameras, A shoots photos and records intersection numbers and directions, shooting of each intersection is completed sequentially, the photos are imported into a computer, identification and identification are automatically carried out by the computer, the distance between the two intersections is calculated according to an image algorithm, and based on direction data and distance data, computer programs automatically generate intersection and road layer data to complete the map.
According to the method, the on-site pictures are shot through the camera, the map primitive data are automatically generated by adopting the computer program for automatic identification and calculation, the working efficiency can be greatly improved, and the input cost is reduced.
The invention can automatically record the road junction path data information through the computer image recognition technology based on the condition of low accuracy requirement of the indoor map, does not need manual point-by-point and line-by-line mapping and manual drawing editing, and has small workload and high reliability.
Through statistical analysis, the indoor map acquisition efficiency can be improved by 4-5 times after the invention is applied, and the reliability is improved by more than 50% compared with the traditional method due to high automation degree and reduced manual intervention. The method has the advantages of clear scheme and simple and convenient operation, related enterprises can improve the existing indoor map acquisition mode on the basis of the existing indoor map acquisition mode with little investment, and the working efficiency is improved.
The invention also provides an indoor map acquisition device based on image recognition, which comprises:
the acquisition unit is used for acquiring scene images shot by the camera at different indoor shooting positions aiming at indoor specific image identifications and identifying target shapes of the specific image identifications in the scene images.
And the processing unit is used for calculating the path distance between corresponding shooting positions or the path distance between the shooting positions and the corresponding specific image mark based on the target shape of the specific image mark in the scene image.
And the execution unit is used for taking the path distance as a unit and automatically generating all map primitive data in the system.
An image processing unit configured to:
performing enhancement processing and noise reduction processing on the scene image; after the image preprocessing, if the computer cannot identify the specific image identification, reminding and displaying the re-shooting mark.
While the invention has been described in detail in the foregoing general description and specific examples, it will be apparent to those skilled in the art that modifications and improvements can be made thereto. Accordingly, such modifications or improvements may be made without departing from the spirit of the invention and are intended to be within the scope of the invention as claimed.
Claims (7)
1. An indoor map acquisition method based on image recognition is characterized by comprising the following steps:
acquiring scene images shot by a camera at different indoor shooting positions aiming at indoor specific image identifications, and identifying target shapes of the specific image identifications in the scene images;
Calculating the path distance between corresponding shooting positions or the path distance between the shooting positions and the corresponding specific image mark based on the target shape of the specific image mark in the scene image;
Taking the path distance as a unit, automatically generating all map primitive data in a system;
The map primitive data includes two kinds of:
the map primitive data are distances between all adjacent two shooting positions: forming roads with a plurality of intersections indoors, respectively fixing the specific image identifications and the shooting positions at any two adjacent intersections when shooting scene images, wherein map primitive data are distances between all adjacent two shooting positions;
The map primitive data is the distance from all shooting positions to the specific image mark: and forming roads with a plurality of intersections in a room, fixing a specific image identifier at one end of the roads in the room, and shooting the scene images at the different intersections on the roads to obtain the map primitive data, wherein the map primitive data are the distances from all shooting positions to the specific image identifier.
2. The indoor map capturing method based on image recognition according to claim 1, wherein the capturing camera further comprises a preprocessing step before the scene images captured for the indoor specific image identification at different indoor capturing positions, comprising:
Manually manufacturing the specific image mark in advance, and calibrating a camera;
The pretreatment step is a step of manual pretreatment.
3. The indoor map collecting method based on image recognition according to claim 1, wherein said step calculates a path distance between corresponding photographing positions based on a target shape of said specific image mark in said scene image, or a path distance from a photographing position to a corresponding said specific image mark, all scene images obtained are imported into a computer for automatic identification and recognition, and said path distance is calculated according to an image algorithm.
4. The indoor map collecting method based on image recognition as claimed in claim 3, wherein the map primitive data is based on azimuth data and distance data, and intersection and road layer data are automatically generated by a computer program to complete the map;
And the specific image mark is a plastic plate with the thickness of 60cm and 60cm, black and white square pictures are posted on the surface of the plastic plate, squares are 3*3, and each small square is 20cm and 20cm.
5. The indoor map collecting method based on image recognition according to claim 1, wherein said step calculates a path distance between corresponding photographing positions or a path distance from a photographing position to a corresponding specific image mark based on a target shape of the specific image mark in the scene image, further comprising an image preprocessing step comprising:
Performing enhancement processing and noise reduction processing on the scene image;
After the image preprocessing step, if the computer cannot identify the specific image identifier, reminding and displaying a re-shooting mark.
6. An indoor map acquisition system based on image recognition, characterized by comprising:
The acquisition unit is used for acquiring scene images shot by the camera at different indoor shooting positions aiming at indoor specific image identifications and identifying target shapes of the specific image identifications in the scene images;
A processing unit, configured to calculate a path distance between corresponding shooting positions, or a path distance between a shooting position and a corresponding specific image identifier, based on a target shape of the specific image identifier in the scene image;
The execution unit is used for automatically generating all map primitive data in the system by taking the path distance as a unit;
The map primitive data includes two kinds of:
the map primitive data are distances between all adjacent two shooting positions: forming roads with a plurality of intersections indoors, respectively fixing the specific image identifications and the shooting positions at any two adjacent intersections when shooting scene images, wherein map primitive data are distances between all adjacent two shooting positions;
The map primitive data is the distance from all shooting positions to the specific image mark: and forming roads with a plurality of intersections in a room, fixing a specific image identifier at one end of the roads in the room, and shooting the scene images at the different intersections on the roads to obtain the map primitive data, wherein the map primitive data are the distances from all shooting positions to the specific image identifier.
7. The image recognition-based indoor map acquisition system of claim 6, further comprising:
an image processing unit configured to:
Performing enhancement processing and noise reduction processing on the scene image;
after the image preprocessing, if the computer cannot identify the specific image identification, reminding and displaying the re-shooting mark.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010737066.4A CN111881824B (en) | 2020-07-28 | 2020-07-28 | Indoor map acquisition method and system based on image recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010737066.4A CN111881824B (en) | 2020-07-28 | 2020-07-28 | Indoor map acquisition method and system based on image recognition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111881824A CN111881824A (en) | 2020-11-03 |
| CN111881824B true CN111881824B (en) | 2024-07-02 |
Family
ID=73200788
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010737066.4A Active CN111881824B (en) | 2020-07-28 | 2020-07-28 | Indoor map acquisition method and system based on image recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111881824B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20150008295A (en) * | 2013-07-12 | 2015-01-22 | 한국교통연구원 | User device locating method and apparatus for the same |
| CN109374008A (en) * | 2018-11-21 | 2019-02-22 | 深动科技（北京）有限公司 | A kind of image capturing system and method based on three mesh cameras |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007206099A (en) * | 2006-01-30 | 2007-08-16 | Mobile Mapping Kk | Map creation support system |
| JP5324240B2 (en) * | 2009-01-29 | 2013-10-23 | 株式会社ゼンリン | Road marking map generation method and road marking map generation device |
| JP4560128B1 (en) * | 2009-08-13 | 2010-10-13 | 株式会社パスコ | Map image integrated database generation system and map image integrated database generation program |
| CN105841687B (en) * | 2015-01-14 | 2019-12-06 | 上海智乘网络科技有限公司 | indoor positioning method and system |
| CN106980633B (en) * | 2016-01-19 | 2020-12-15 | 阿里巴巴（中国）有限公司 | Indoor map data generation method and device |
-
2020
- 2020-07-28 CN CN202010737066.4A patent/CN111881824B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20150008295A (en) * | 2013-07-12 | 2015-01-22 | 한국교통연구원 | User device locating method and apparatus for the same |
| CN109374008A (en) * | 2018-11-21 | 2019-02-22 | 深动科技（北京）有限公司 | A kind of image capturing system and method based on three mesh cameras |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111881824A (en) | 2020-11-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Golparvar-Fard et al. | Evaluation of image-based modeling and laser scanning accuracy for emerging automated performance monitoring techniques | |
| CN103366250B (en) | City appearance environment detection method based on three-dimensional live-action data and system | |
| Rashidi et al. | Generating absolute-scale point cloud data of built infrastructure scenes using a monocular camera setting | |
| CN109949365B (en) | Vehicle designated position parking method and system based on road surface feature points | |
| CN108839016B (en) | Robot inspection method, storage medium, computer equipment and inspection robot | |
| CN111192331A (en) | External parameter calibration method and device for laser radar and camera | |
| CN104173054A (en) | Measuring method and measuring device for height of human body based on binocular vision technique | |
| WO2020220522A1 (en) | Intelligent visual sampling method, system and device | |
| CN109859269B (en) | Shore-based video auxiliary positioning unmanned aerial vehicle large-range flow field measuring method and device | |
| KR20160117143A (en) | Method, device and system for generating an indoor two dimensional plan view image | |
| CN113469178B (en) | Power meter identification method based on deep learning | |
| CN114492070A (en) | High-precision mapping geographic information virtual simulation technology and device | |
| CN113656477A (en) | Method for verifying and fusing multi-source heterogeneous data of homeland space | |
| CN112902869B (en) | Method and device for adjusting laser plane of rail profile measuring system | |
| CN114037762A (en) | Real-time high-precision positioning method based on image and high-precision map registration | |
| CN111881824B (en) | Indoor map acquisition method and system based on image recognition | |
| CN111758118B (en) | Visual positioning method, device, equipment and readable storage medium | |
| CN113420109A (en) | Method for measuring permeability of street interface, computer and storage medium | |
| CN116645404B (en) | Photo GPS position information extraction matching method and extraction matching device | |
| CN114693782A (en) | Method and device for determining conversion relation between three-dimensional scene model coordinate system and physical coordinate system | |
| CN113190564A (en) | Map updating system, method and device | |
| JP2011170400A (en) | Program, method, and apparatus for identifying facility | |
| CN116403183A (en) | Obstacle position determination method and storage medium | |
| CN111598956A (en) | Calibration method, device and system | |
| CN114791282A (en) | Road facility coordinate calibration method and device based on vehicle high-precision positioning |
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 |