CN112362070A - Vehicle navigation method and device - Google Patents
Vehicle navigation method and device Download PDFInfo
- Publication number
- CN112362070A CN112362070A CN202011101551.9A CN202011101551A CN112362070A CN 112362070 A CN112362070 A CN 112362070A CN 202011101551 A CN202011101551 A CN 202011101551A CN 112362070 A CN112362070 A CN 112362070A
- Authority
- CN
- China
- Prior art keywords
- landmark
- model
- real
- road sign
- time
- 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
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000000926 separation method Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 8
- 238000013527 convolutional neural network Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 6
- 230000010485 coping Effects 0.000 abstract 1
- 238000003708 edge detection Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000003709 image segmentation Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
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
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/28—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network with correlation of data from several navigational instruments
- G01C21/30—Map- or contour-matching
-
- 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
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/36—Input/output arrangements for on-board computers
- G01C21/3626—Details of the output of route guidance instructions
- G01C21/3644—Landmark guidance, e.g. using POIs or conspicuous other objects
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Navigation (AREA)
Abstract
The invention relates to the technical field of navigation, and discloses a vehicle navigation method, which comprises the following steps: establishing an electronic map comprising a landmark model; acquiring a real-time driving image, and separating real-time road sign information from the real-time driving image; acquiring real-time position information, and acquiring a landmark model set in a circle with the position information as a circle center and a set distance as a radius from the electronic map; comparing the real-time landmark information with landmark models in the landmark model set to obtain a matched landmark model; and outputting and displaying the road sign model positioned in front of the matched road sign model along the driving direction. The invention has the technical effects of coping with complex terrain and high intersection navigation precision.
Description
Technical Field
The invention relates to the technical field of navigation, in particular to a vehicle navigation method and device.
Background
The vehicle navigation technology is realized based on GPS positioning. The vehicle navigation can conveniently and accurately tell the user to the path to the destination and carry out voice broadcast reminding, thereby greatly facilitating the life of people. However, when the current vehicle-mounted navigation meets the conditions of complex intersections, complex terrains and the like, the problem of inaccurate navigation often occurs. Particularly, currently, navigation usually cannot identify positioning information in height, and when viaducts, loops and the like relate to complex intersections or terrains with different heights, the navigation gives accurate reminding to a driver, and whether a driving route of the driver is correct or not cannot be quickly judged, so that a navigation error is caused.
Disclosure of Invention
The invention aims to overcome the technical defects and provide a vehicle navigation method, which solves the technical problem of low navigation precision at complex intersections and terrains in the prior art.
In order to achieve the technical purpose, the technical scheme of the invention provides a vehicle navigation method, which comprises the following steps:
establishing an electronic map comprising a landmark model;
acquiring a real-time driving image, and separating real-time road sign information from the real-time driving image;
acquiring real-time position information, and acquiring a landmark model set in a circle with the position information as a circle center and a set distance as a radius from the electronic map;
comparing the real-time landmark information with landmark models in the landmark model set to obtain a matched landmark model;
and outputting and displaying the road sign model positioned in front of the matched road sign model along the driving direction.
The invention also provides a vehicle navigation device, which comprises a processor and a memory, wherein the memory is stored with a computer program, and the computer program realizes the vehicle navigation method when being executed by the processor.
The present invention also provides a computer storage medium having a computer program stored thereon, which, when executed by a processor, implements the vehicle navigation method.
Compared with the prior art, the invention has the beneficial effects that: the invention firstly establishes an electronic map comprising a road sign model, then separates real-time road sign information from a real-time driving image, further obtains a road sign model near the current real-time position, confirms the current position of a vehicle through the comparison and matching of the road sign information and the near road sign model, realizes the accurate positioning of the vehicle, and particularly can realize the accurate positioning of the vehicle on the height. After the accurate positioning of the vehicle is realized, the road sign models along the road are displayed, so that a driver can visually observe the terrain of the current road condition, the driver can be helped to accurately judge the driving route, and the phenomenon of navigation error is avoided.
Drawings
Fig. 1 is a flowchart of an embodiment of a vehicle navigation method according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Example 1
As shown in fig. 1, embodiment 1 of the present invention provides a vehicle navigation method including the steps of:
s1, establishing an electronic map comprising a landmark model;
s2, acquiring a real-time driving image, and separating real-time road sign information from the real-time driving image;
s3, acquiring real-time position information, and acquiring a landmark model set in a circle with the position information as the center of the circle and a set distance as the radius from the electronic map;
s4, comparing the real-time landmark information with landmark models in the landmark model set to obtain a matched landmark model;
and S5, outputting and displaying the landmark model positioned in front of the matched landmark model along the driving direction.
The embodiment of the invention firstly establishes the electronic map comprising the landmark model, then separates the real-time landmark information from the real-time driving image, further obtains the landmark model near the current real-time position, confirms the current position of the vehicle through the contrast matching of the landmark information and the nearby landmark model, realizes the accurate positioning of the vehicle and provides accurate position information for navigation. The vehicle location that this embodiment provided is aided with the road sign location on GPS location's basis for positioning accuracy improves greatly. Particularly, for two roads at the same position and different heights, the method provided by the embodiment can make up for the deficiency of GPS positioning, and accurately judge the road and the position of the vehicle. After the accurate positioning of the vehicle is realized, the road sign models along the road are displayed, and the driving navigation is realized through the displayed road sign models. The driver can visually observe the terrain of the current road condition through the road sign model, and visually and accurately judge the direction to be driven and the road, so that the navigation error phenomenon is avoided.
It should be understood that the vehicle navigation method provided by the invention can independently realize navigation, and can also be matched with other existing navigation methods to realize dual navigation, so that the navigation precision is higher.
Preferably, the electronic map including the landmark model is established, specifically:
acquiring a scene image comprising a road sign, and separating the road sign model from the scene image;
and associating the landmark models with the corresponding positioning information to obtain the electronic map.
And obtaining the electronic map containing the landmark models according to the corresponding relation between the landmark models and the positioning information. And the road sign model at the corresponding position can be conveniently obtained through the positioning information subsequently.
Preferably, the road sign models include a building model, a road surface indicating line model, a road sign model, and a traffic light model.
The road sign model is selected according to specific route scene setting so as to be easily distinguished as excellent. Particularly, for two roads at the same position and different heights, the road sign models at the road junction are selected to be the target of distinguishing the road signs obviously and easily, and the same is also selected for the road sign models of different road sections on the same road. The road sign models are easy to distinguish, the difficulty of subsequent matching is reduced, and a driver can conveniently and quickly judge the route according to the road sign models.
Preferably, the method comprises the steps of obtaining a real-time driving image, and separating real-time road sign information from the real-time driving image, and specifically comprises the following steps:
taking the scene image as input and the road sign model as output, and training a convolutional neural network to obtain a road sign separation model;
and inputting the real-time driving image into the road sign separation model to obtain the real-time road sign information.
At present, a threshold method, an edge detection method, a filtering method and the like are generally adopted for image segmentation, but the algorithm complexity of the methods is high, and the methods are not suitable for the requirement of real-time image segmentation. In the embodiment, the scene image acquired when the electronic map is built and the segmented road sign model are used as sample data for training, the road sign separation model is built, the background features in the real-time driving image are quickly separated through the road sign separation model, the real-time road sign information is obtained, and the requirement for implementing the quick real-time separation of the driving image is met. For the separation of the scene images, the above mentioned threshold method, edge detection method, filtering method, etc. can be selected to implement.
The landmark information separated by the landmark separation model in this embodiment is a signpost S1 and a building S2.
Preferably, the real-time landmark information is compared with landmark models in the landmark model set to obtain matched landmark models, and the method specifically comprises the following steps:
selecting a plurality of matching attributes, obtaining the attribute value of the real-time landmark information and the attribute value of each landmark model in the landmark model set, respectively calculating the attribute similarity of the real-time landmark information and each landmark model, and taking the landmark model with the maximum attribute similarity as the matching landmark model.
Specifically, different weight values can be assigned to each matching attribute, the similarity of the implementation landmark information and the landmark model with respect to each matching attribute is calculated respectively, and then the similarity weighted sum of each attribute is calculated to obtain the attribute similarity. The similarity of each matching attribute can be calculated by Euclidean distance similarity, cosine similarity or grey correlation similarity. The matching attribute may select a color attribute, a contour attribute, a feature point attribute, and the like.
In this embodiment, the landmark model matched with the signpost S1 is a1, and the landmark model matched with the building S2 is S2.
Preferably, outputting and displaying a road sign model located in front of the matched road sign model along the driving direction, specifically;
and planning a driving route by taking the matched landmark model as a starting point, acquiring all landmark models on the driving route, and sequentially displaying all the landmark models.
After the road sign models are matched at the starting points, the road sign models along the way are sequentially displayed according to the planned form route, and the accurate navigation effect can be achieved. The driver can quickly judge the accurate advancing direction and road through simple comparison. And displaying a landmark model A3 in front of the landmark model A1 and the landmark model A2, wherein the landmark model A3 is positioned on a road D1, and a driver can quickly judge that the driver should drive to the road D1 through the displayed landmark model A3, so that a landmark navigation effect is realized. At this time, if there is another road D2, the road D2 is located at the same position as the road D1, the road D2 is located above the road D1, and the driver can easily exclude the road D2 according to the landmark model A3 and correctly navigate to the road D1.
Preferably, the displaying of the road sign models is performed in sequence, specifically:
the method comprises the steps of obtaining real-time position information and driving direction of a vehicle, obtaining a road sign model which is located in front of the vehicle and is closest to the vehicle, and displaying the road sign model.
And the road sign model closest to the real-time position is acquired and displayed, so that the road sign model can be displayed in advance, and the driver can conveniently prejudge in advance. The road sign model at the complex terrain such as corners, bifurcations, high-rise bridges, circular lines and the like is preferably highlighted, for example, displayed in a flashing manner, so as to warn the driver.
Example 2
Embodiment 2 of the present invention provides a vehicle navigation device including a processor and a memory, the memory having stored thereon a computer program that, when executed by the processor, implements the vehicle navigation method provided in the above embodiment.
The vehicle navigation method specifically comprises the following steps:
establishing an electronic map comprising a landmark model;
acquiring a real-time driving image, and separating real-time road sign information from the real-time driving image;
acquiring real-time position information, and acquiring a landmark model set in a circle with the position information as a circle center and a set distance as a radius from the electronic map;
comparing the real-time landmark information with landmark models in the landmark model set to obtain a matched landmark model;
and outputting and displaying the road sign model positioned in front of the matched road sign model along the driving direction.
The vehicle navigation device provided by the invention is used for realizing the vehicle navigation method, so that the vehicle navigation device has the technical effects which are also possessed by the vehicle navigation method, and the details are not repeated herein.
Example 3
Embodiment 3 of the present invention provides a computer storage medium having stored thereon a computer program that, when executed by a processor, implements the vehicle navigation method provided in the above embodiment.
The vehicle navigation method specifically comprises the following steps:
establishing an electronic map comprising a landmark model;
acquiring a real-time driving image, and separating real-time road sign information from the real-time driving image;
acquiring real-time position information, and acquiring a landmark model set in a circle with the position information as a circle center and a set distance as a radius from the electronic map;
comparing the real-time landmark information with landmark models in the landmark model set to obtain a matched landmark model;
and outputting and displaying the road sign model positioned in front of the matched road sign model along the driving direction.
The computer storage medium provided by the invention is used for realizing the vehicle navigation method, so that the technical effects of the vehicle navigation method are achieved, and the computer storage medium also has the technical effects, and the details are not repeated herein.
The above-described embodiments of the present invention should not be construed as limiting the scope of the present invention. Any other corresponding changes and modifications made according to the technical idea of the present invention should be included in the protection scope of the claims of the present invention.
Claims (9)
1. A vehicle navigation method, characterized by comprising the steps of:
establishing an electronic map comprising a landmark model;
acquiring a real-time driving image, and separating real-time road sign information from the real-time driving image;
acquiring real-time position information, and acquiring a landmark model set in a circle with the position information as a circle center and a set distance as a radius from the electronic map;
comparing the real-time landmark information with landmark models in the landmark model set to obtain a matched landmark model;
and outputting and displaying the road sign model positioned in front of the matched road sign model along the driving direction.
2. The vehicle navigation method according to claim 1, wherein the electronic map including the landmark model is created, specifically:
acquiring a scene image comprising a road sign, and separating the road sign model from the scene image;
and associating the landmark models with the corresponding positioning information to obtain the electronic map.
3. The vehicle navigation method of claim 2, wherein the road sign model includes a building model, a road surface indication line model, a guideboard model, and a traffic light model.
4. The vehicle navigation method according to claim 2, wherein the real-time driving image is acquired, and the real-time landmark information is separated from the real-time driving image, specifically:
taking the scene image as input and the road sign model as output, and training a convolutional neural network to obtain a road sign separation model;
and inputting the real-time driving image into the road sign separation model to obtain the real-time road sign information.
5. The vehicle navigation method according to claim 1, wherein the real-time landmark information is compared with landmark models in the landmark model set to obtain matched landmark models, specifically:
selecting a plurality of matching attributes, obtaining the attribute value of the real-time landmark information and the attribute value of each landmark model in the landmark model set, respectively calculating the attribute similarity between each landmark model in the landmark model set and the real-time landmark information, and taking the landmark model with the maximum attribute similarity as the matching landmark model.
6. The vehicle navigation method according to claim 1, wherein a landmark model located ahead of the matched landmark model in a driving direction is output and displayed, specifically;
and planning a driving route by taking the matched landmark model as a starting point, acquiring all landmark models on the driving route, and sequentially displaying all the landmark models.
7. The vehicle navigation method according to claim 6, wherein each of the landmark models is displayed in sequence, specifically:
the method comprises the steps of obtaining real-time position information and driving direction of a vehicle, obtaining a road sign model which is located in front of the vehicle and is closest to the vehicle, and displaying the road sign model.
8. A vehicle navigation device comprising a processor and a memory, the memory having stored thereon a computer program that, when executed by the processor, implements a vehicle navigation method as recited in any one of claims 1-7.
9. A computer storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements a vehicle navigation method as claimed in any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011101551.9A CN112362070A (en) | 2020-10-15 | 2020-10-15 | Vehicle navigation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011101551.9A CN112362070A (en) | 2020-10-15 | 2020-10-15 | Vehicle navigation method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112362070A true CN112362070A (en) | 2021-02-12 |
Family
ID=74507678
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011101551.9A Pending CN112362070A (en) | 2020-10-15 | 2020-10-15 | Vehicle navigation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112362070A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108871366A (en) * | 2018-07-10 | 2018-11-23 | 京东方科技集团股份有限公司 | Landmark navigation method and system based on shutter glasses |
| CN109029488A (en) * | 2018-06-29 | 2018-12-18 | 百度在线网络技术（北京）有限公司 | Navigating electronic map generating method, equipment and storage medium |
| CN109212571A (en) * | 2017-06-29 | 2019-01-15 | 沈阳新松机器人自动化股份有限公司 | Navigation locating method and device |
| CN109556625A (en) * | 2018-11-30 | 2019-04-02 | 努比亚技术有限公司 | Air navigation aid, device, navigation equipment and storage medium based on front windshield |
| CN109579867A (en) * | 2018-11-30 | 2019-04-05 | 惠州市德赛西威汽车电子股份有限公司 | A kind of air navigation aid and its system with marker prompt |
| CN110530385A (en) * | 2019-08-21 | 2019-12-03 | 西安华运天成通讯科技有限公司 | City navigation method and its system based on image recognition |
| CN111259818A (en) * | 2020-01-18 | 2020-06-09 | 苏州浪潮智能科技有限公司 | Road sign identification method, system and device |
| CN111380542A (en) * | 2018-12-28 | 2020-07-07 | 沈阳美行科技有限公司 | Vehicle positioning and navigation method and device and related system |
| CN111766619A (en) * | 2020-05-26 | 2020-10-13 | 江苏集萃移动通信技术研究所有限公司 | Road sign intelligent identification assisted fusion navigation positioning method and device |
-
2020
- 2020-10-15 CN CN202011101551.9A patent/CN112362070A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109212571A (en) * | 2017-06-29 | 2019-01-15 | 沈阳新松机器人自动化股份有限公司 | Navigation locating method and device |
| CN109029488A (en) * | 2018-06-29 | 2018-12-18 | 百度在线网络技术（北京）有限公司 | Navigating electronic map generating method, equipment and storage medium |
| CN108871366A (en) * | 2018-07-10 | 2018-11-23 | 京东方科技集团股份有限公司 | Landmark navigation method and system based on shutter glasses |
| CN109556625A (en) * | 2018-11-30 | 2019-04-02 | 努比亚技术有限公司 | Air navigation aid, device, navigation equipment and storage medium based on front windshield |
| CN109579867A (en) * | 2018-11-30 | 2019-04-05 | 惠州市德赛西威汽车电子股份有限公司 | A kind of air navigation aid and its system with marker prompt |
| CN111380542A (en) * | 2018-12-28 | 2020-07-07 | 沈阳美行科技有限公司 | Vehicle positioning and navigation method and device and related system |
| CN110530385A (en) * | 2019-08-21 | 2019-12-03 | 西安华运天成通讯科技有限公司 | City navigation method and its system based on image recognition |
| CN111259818A (en) * | 2020-01-18 | 2020-06-09 | 苏州浪潮智能科技有限公司 | Road sign identification method, system and device |
| CN111766619A (en) * | 2020-05-26 | 2020-10-13 | 江苏集萃移动通信技术研究所有限公司 | Road sign intelligent identification assisted fusion navigation positioning method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10628671B2 (en) | Road modeling from overhead imagery | |
| EP3673407B1 (en) | Automatic occlusion detection in road network data | |
| US10699135B2 (en) | Automatic localization geometry generator for stripe-shaped objects | |
| US11093759B2 (en) | Automatic identification of roadside objects for localization | |
| US20190078905A1 (en) | Systems and methods for using real-time imagery in navigation | |
| EP2162849B1 (en) | Lane determining device, lane determining method and navigation apparatus using the same | |
| KR102595897B1 (en) | Method and apparatus of determining road line | |
| CN108388641B (en) | Traffic facility map generation method and system based on deep learning | |
| JP4703605B2 (en) | Feature extraction method, image recognition method and feature database creation method using the same | |
| JP2019139762A (en) | Method for providing information for vehicle travel | |
| EP3660737A1 (en) | Method, apparatus, and system for providing image labeling for cross view alignment | |
| EP2372605A2 (en) | Image processing system and position measurement system | |
| US10942519B2 (en) | System and method for navigating an autonomous driving vehicle | |
| JP2008250687A (en) | Feature information collection device and feature information collection method | |
| CN114509065B (en) | Map construction method, system, vehicle terminal, server and storage medium | |
| CN113358125B (en) | Navigation method and system based on environment target detection and environment target map | |
| EP1367368B1 (en) | Bearing data for route guidance | |
| CN112418081B (en) | Method and system for quickly surveying traffic accidents by air-ground combination | |
| CN110969592A (en) | Image fusion method, automatic driving control method, device and equipment | |
| JP2009099125A (en) | Image recognition device, image recognition program, and point information collection device and navigation device using them | |
| EP4273501A1 (en) | Method, apparatus, and computer program product for map data generation from probe data imagery | |
| CN112781600A (en) | Vehicle navigation method, device and storage medium | |
| CN112432650A (en) | Acquisition method of high-precision map data, vehicle control method and device | |
| CN115406453A (en) | Navigation method, navigation device and computer storage medium | |
| CN112362070A (en) | Vehicle navigation method and device |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210212 |
|
| RJ01 | Rejection of invention patent application after publication |