CN106441343B - Street view navigation method based on character recognition - Google Patents
Street view navigation method based on character recognition Download PDFInfo
- Publication number
- CN106441343B CN106441343B CN201610794146.7A CN201610794146A CN106441343B CN 106441343 B CN106441343 B CN 106441343B CN 201610794146 A CN201610794146 A CN 201610794146A CN 106441343 B CN106441343 B CN 106441343B
- Authority
- CN
- China
- Prior art keywords
- destination
- street view
- view image
- meters
- navigation
- 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
- G01C21/26—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
- G01C21/3647—Guidance involving output of stored or live camera images or video streams
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Navigation (AREA)
Abstract
On the basis of the existing map navigation, the character recognition of all street view images in a certain range (periphery) of a destination is added, a street view image containing the name of the destination is obtained, and the street view image is placed into a cache for standby; and after the navigation is started, when the destination is about to be reached and the distance is m meters away from the destination, acquiring a street view image containing the name of the destination and carrying out merging display on the street view image and a map navigation interface. Therefore, the identified accurate destination street view image is provided m meters before the destination is reached, the seen street view destination street view images can be easily compared, the specific position of the destination can be quickly and accurately found, and the user experience is improved.
Description
Technical Field
The invention belongs to the technical field of navigation, and particularly relates to a street view navigation method based on character recognition.
Background
Navigation systems are a collection of basic functions including "positioning", "destination selection", "route calculation", and "route guidance".
The map navigation brings comfort and convenience to people, and people in different places can find the sense of safety by the map navigation. At present, people highly depend on a map navigation system, and meanwhile, further innovation of the existing map navigation system is expected, so that the accuracy and the user experience of the map navigation system are further improved.
In the conventional map navigation method, as shown in fig. 1, a location of a user is located or a starting point is input by the user, a destination is input, then a map navigation system starts to search for a destination position, route planning is performed according to the positions of the starting point and the destination, all possible routes are provided for the user, and when the user selects a satisfactory route, the map navigation system starts to navigate according to the selected route.
Traditional map navigation presents a complex path background in a simple and clear way in the real situation, but at the same time, the simplicity is at the expense of precision and user experience. In the urban area with high-rise standing and scale-to-scale ratio, map navigation brings troubles for users, and people cannot accurately arrive at a destination;
with the updated development of the technology, satellite road network navigation appears in the navigation system, and the satellite road network navigation is the same as the navigation method shown in fig. 1, so that a route map shown in fig. 2 is obtained.
Except that during navigation, the user may open a satellite road network graph as shown in fig. 3. The surrounding environment has stereoscopic impression, and is not only simple and simple grid indication.
As shown in fig. 3, we have a sense of being personally on the scene visually, and we can actually compare the surrounding background under the guidance of navigation, and the route to the destination is more efficient for users. Firstly, the current satellite road network resolution is not high, which can be seen from fig. 3, and the positioning of the destination is influenced; secondly, the satellite road network has a great difference with the walking visual angle of people in a overlooking mode, and the practical effect is naturally poor.
Although the satellite road network navigation has satisfied the travel demand of people to a great extent, the navigation precision is still very deficient. The current navigation system mainly adopts GPS positioning, the precision of the GPS positioning is generally 10-20 meters, when the destination is some relatively precise units, such as supermarkets, convenience stores and the like, the GPS navigation system can only position the approximate positions of the units, and when the nearby streets are relatively complicated, the GPS navigation system needs to spend a great deal of time to find specific positions nearby. Although the functions of street view maps are developed in the conventional maps, the street view maps do not have a search function and cannot solve the problems.
We can see the surroundings of the "university of electronic technology" destination we want to reach through the street view. From the two exemplary drawings of street environment in fig. 4(a) and (b), we can see that the surrounding scale-to-bar ratio of "electronic technology university" can only reach the vicinity of the destination and can not find the specific location of the destination when we navigate through the two former maps. Especially, in a state of high concentration of driving spirit, a few seconds for the probe to find a destination may miss the target or cause an accident.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a street view navigation method based on character recognition, so that a user can accurately and efficiently find a specific position of a destination and the user experience is improved.
In order to achieve the above object, the street view navigation method based on character recognition of the present invention further comprises the following steps:
after the destination is input and the destination position is found, all street view images in a certain range (the range can be set according to specific requirements) near the destination are subjected to character recognition, a street view image containing the destination name is found or designated, and the street view image is placed into a cache for standby;
and when the distance between the street view image and the destination is m meters after the navigation is started, acquiring the street view image containing the destination name and carrying out combined display on the street view image and the map navigation interface.
The object of the invention is thus achieved.
Aiming at the problems in the prior art, the invention adds character recognition of all street view images in a certain range (periphery) of a destination on the basis of the existing map navigation to obtain a street view image containing the name of the destination, and the street view image is put into a cache for standby; after navigation is started, when the user is about to reach a destination, when the user is m meters away from the destination (m can be set according to specific conditions or set by a user), street view images containing the name of the destination are acquired and are merged with a map navigation interface for display. Therefore, the identified accurate destination street view image is provided m meters before the destination is reached, the seen street view destination street view images can be easily compared, the specific position of the destination can be quickly and accurately found, and the user experience is improved.
Drawings
FIG. 1 is a starting point path navigation diagram of a specific example of existing map navigation;
FIG. 2 is a starting point path navigation diagram of an embodiment of satellite road network navigation;
FIG. 3 is a starting point satellite road network navigation map of an embodiment of satellite road network navigation;
FIG. 4 is two example diagrams of a complex street environment at a target site;
FIG. 5 is a flowchart of an embodiment of a street view navigation method based on character recognition according to the present invention;
FIG. 6 is an example diagram of a street view image found with a destination name;
FIG. 7 is an example diagram of a street view image 250 meters from a destination merged with a map navigation interface for display at an additional 300 meters distance from the destination;
FIG. 8 is an example diagram of a street view image 50 meters from a destination merged with a map navigation interface for display at a distance of 250 meters from the destination;
fig. 9 is an example diagram of a street view image containing a destination name and a map navigation interface merged for display when the distance from the destination is 50 meters.
Detailed Description
The following description of the embodiments of the present invention is provided in order to better understand the present invention for those skilled in the art with reference to the accompanying drawings. It is to be expressly noted that in the following description, a detailed description of known functions and designs will be omitted when it may obscure the subject matter of the present invention.
Example 1
In this embodiment, the invention also needs to obtain a street view image m + k meters away from the destination on the leading route;
after navigation is started, when the destination is about to be reached, namely the distance is n meters and n is greater than m + k, the street view image which is m + k meters away from the destination on the navigation route is acquired and is merged with the map navigation interface for display.
In this embodiment, after the navigation system reaches a position near the destination, that is, n meters, through the conventional navigation system (as shown in fig. 1), the street view image cached in advance on the navigation route in the navigation system and m meters away from the destination is obtained, and when the street view image is m meters away from the destination, the street view image with the name of the destination is found or specified by capturing the identification text through the text area of the street view image, so that the searched destination is accurately located, the specific position of the destination is quickly and accurately found, and the user experience is improved.
Example 2
FIG. 5 is a flowchart of an embodiment of the street view navigation method based on character recognition according to the present invention.
In this embodiment, the street view navigation method based on character recognition of the present invention includes the following specific steps:
s1, positioning the location of the user or inputting the starting location and positioning by the user, inputting the destination, and then the map navigation system starts to search the position of the destination.
In the present invention, the destination may be specific to an entity on a street, such as a precise unit of a store, supermarket, restaurant, university, etc. This is not the case with conventional map navigation.
And S2, planning the route according to the positions of the starting point and the destination, providing all possible routes for the user, and after the user selects a satisfactory route (if the user does not select the default route given by the map navigation system), starting navigation by the map navigation system according to the selected route or the default route (navigation route) and displaying a map navigation interface. In this embodiment, as shown in fig. 1, the starting place is the east station of Chengdu and the destination is the university of electronic technology.
At the moment, a traditional map navigation mode is adopted, the navigation mode is convenient and fast, and the interference of excessive intermediate information on all users including a driver is eliminated.
Meanwhile, steps S1 and S2 are prior art, and the detailed implementation process thereof is not described herein.
And S3, inputting the destination and finding the destination position, then performing character recognition on all street view images within a certain range (the range can be set according to specific requirements or can be set by a user and can be 30-50 meters) near the destination, finding a street view image containing the name of the destination, and putting the street view image into a cache for later use. In this embodiment, the character recognition is performed in a natural scene.
In this embodiment, the street view image character recognition uses the MSER algorithm, and through preliminary detection, region labeling based on geometric properties, region labeling based on stroke width properties, suspected text region labeling, and segmentation of all characters in the image, and character recognition in a natural scene, then a street view image with characters of "university of electronic technology" is searched, all street view images with characters of "university of electronic technology" are listed, and a street view image with a destination name is found, as shown in fig. 6, and is placed into a cache for standby. Image and text recognition belongs to the prior art, and is not described in detail herein.
S4, in this embodiment, in order to achieve a better search effect, multiple street view images with gradually decreasing distances to the destination are also acquired on the route guidance route at a distance greater than or equal to m meters and less than or equal to m + k meters from the destination.
The number of the specific street view can be set according to specific conditions or user preferences, and too much number can affect the driving of the vehicle by the driver. In the present embodiment, a street view image is located at a distance of m meters, i.e., 50 meters from the destination, and a street view image is located at a distance of m + k meters, i.e., 250 meters from the destination.
At a certain position (generally 50 meters according to design or user preference) before the street view image farthest from the destination, merging and displaying the street view image and the map navigation interface, and when the street view image reaches the position of the farthest street view image, merging and displaying the next, i.e. next, street view image and the map navigation interface, so that the street view image m meters away from the destination is the street view image containing the destination name. In this embodiment, the following steps are specifically performed:
s5, when the destination is about to be reached, that is, the distance is 300 meters, merging the street view image of the off-destination 250 meters with the map navigation interface for display, as shown in fig. 7 in this embodiment. At this time, the street view image navigation is performed in the reverse order, and the direction of the destination is prompted by voice, which is the right side in this embodiment.
S6, when the navigation starts, and the destination is about to be reached, that is, the distance is 250 meters from the destination, merging and displaying the street view image that is acquired on the guidance route and is 50 meters from the destination with the map navigation interface, in this embodiment, as shown in fig. 8.
S7, when the distance is m meters, i.e. 50 meters from the destination, acquiring a street view image containing the destination name and performing a merged display with the map navigation interface, in this embodiment, as shown in fig. 9.
And S8, arriving at the destination, and ending.
After the destination is identified through the street view, the street view navigation realizes accurate navigation, gets through the last blind area between the user and the destination, and realizes that the user is sent to the door.
Although illustrative embodiments of the present invention have been described above to facilitate the understanding of the present invention by those skilled in the art, it should be understood that the present invention is not limited to the scope of the embodiments, and various changes may be made apparent to those skilled in the art as long as they are within the spirit and scope of the present invention as defined and defined by the appended claims, and all matters of the invention which utilize the inventive concepts are protected.
Claims (5)
1. A street view navigation method based on character recognition is characterized by further comprising the following steps:
after the destination is input and the destination position is found, character recognition is carried out on all street view images in a certain range near the destination, a pair of street view images containing the destination name is found or designated, and the street view images are placed into a cache for standby;
and when the distance between the street view image and the destination is m meters after the navigation is started, acquiring the street view image containing the destination name and carrying out combined display on the street view image and the map navigation interface.
2. The streetscape navigation method according to claim 1, wherein the certain range is a 50 m range.
3. The streetscape navigation method according to claim 1, further comprising obtaining streetscape images m + k meters away from the destination on the route guidance route;
after navigation is started, when the destination is about to be reached, namely the distance is n meters and n is greater than m + k, the street view image which is m + k meters away from the destination on the navigation route is acquired and is merged with the map navigation interface for display.
4. The streetscape navigation method according to claim 3, wherein a plurality of streetscape images with gradually decreasing distance from the destination are also acquired on the route guidance route at a distance greater than or equal to m meters and less than or equal to m + k meters from the destination;
and merging and displaying the street view and the map navigation interface at a certain position before the street view image which is farthest away from the destination, and merging and displaying the next, namely next, far street view image and the map navigation interface when the street view image reaches the position of the farthest street view image, so that the street view image m meters away from the destination is the street view image containing the destination name.
5. The streetscape navigation method according to claim 4, wherein m is 50, k is 200, streetscape images are obtained at a distance of 250 meters from the destination on the route guidance route, streetscape images are obtained at a distance of 50 meters from the destination on the route guidance route;
merging and displaying the street view image which is the farthest away from the destination and a map navigation interface at a position 50 meters before the street view image which is the farthest away from the destination and is 250 meters away from the destination; at the distance of 250 meters from the destination, merging and displaying the street view image which is 50 meters away from the destination and a map navigation interface; and at the distance of 50 meters from the destination, merging and displaying the street view image containing the destination name and the map navigation interface.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610794146.7A CN106441343B (en) | 2016-08-31 | 2016-08-31 | Street view navigation method based on character recognition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610794146.7A CN106441343B (en) | 2016-08-31 | 2016-08-31 | Street view navigation method based on character recognition |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106441343A CN106441343A (en) | 2017-02-22 |
CN106441343B true CN106441343B (en) | 2020-07-17 |
Family
ID=58163730
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610794146.7A Active CN106441343B (en) | 2016-08-31 | 2016-08-31 | Street view navigation method based on character recognition |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106441343B (en) |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107014393A (en) * | 2017-05-24 | 2017-08-04 | 刘兴丹 | A kind of method of image map navigation, device |
CN110345954A (en) * | 2018-04-03 | 2019-10-18 | 奥迪股份公司 | Navigation system and method |
CN108478398B (en) * | 2018-05-17 | 2023-12-29 | 中兴健康科技有限公司 | Manual blind guiding system and blind guiding method |
CN110954064A (en) * | 2018-09-27 | 2020-04-03 | 北京嘀嘀无限科技发展有限公司 | Positioning method and positioning device |
CN114323056A (en) * | 2020-09-30 | 2022-04-12 | 比亚迪股份有限公司 | Driving navigation method and device and automobile |
CN113298001A (en) * | 2021-06-02 | 2021-08-24 | 上海大学 | System and method for identifying and recommending shops along street based on vehicle-mounted camera shooting |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101118162A (en) * | 2007-09-18 | 2008-02-06 | 倚天资讯股份有限公司 | System of realistic navigation combining landmark information, user interface and method |
CN102200448A (en) * | 2011-03-04 | 2011-09-28 | 鸿富锦精密工业(深圳)有限公司 | Positioning and navigation device |
CN102519478A (en) * | 2011-11-16 | 2012-06-27 | 深圳市凯立德科技股份有限公司 | Streetscape destination guiding method and device |
CN103105174A (en) * | 2013-01-29 | 2013-05-15 | 四川长虹佳华信息产品有限责任公司 | AR (augmented reality)-based vehicle-mounted live-action safe navigation method |
CN103134499A (en) * | 2013-02-06 | 2013-06-05 | 腾讯科技(深圳)有限公司 | Navigation method and navigation device |
CN103674016A (en) * | 2013-12-16 | 2014-03-26 | 广东步步高电子工业有限公司 | Walking guide system based on mobile terminal and implementation method of walking guide system |
CN104515529A (en) * | 2013-09-27 | 2015-04-15 | 高德软件有限公司 | Real-scenery navigation method and navigation equipment |
EP2889581A1 (en) * | 2012-09-20 | 2015-07-01 | Huawei Device Co., Ltd. | Navigation terminal, navigation method and remote navigation service system |
CN104850563A (en) * | 2014-02-18 | 2015-08-19 | 歌乐株式会社 | Destination image comparison retrieval device, destination image comparison retrieval system and destination image comparison retrieval method |
CN104966065A (en) * | 2015-06-23 | 2015-10-07 | 电子科技大学 | Target recognition method and device |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102243078B (en) * | 2010-05-13 | 2016-03-30 | 上海宾华信息科技有限公司 | Namely a kind of institute depending on releasing type guider and implementation method |
CN105890616A (en) * | 2013-07-11 | 2016-08-24 | 北京奇虎科技有限公司 | Method and system for realizing route guidance through street view |
CN105180919A (en) * | 2015-05-21 | 2015-12-23 | 小驴科技(北京)有限公司 | Position information based operation method and device |
CN104998376A (en) * | 2015-07-13 | 2015-10-28 | 福州大学 | Virtual reality technology-based scenery viewing system |
CN105222792A (en) * | 2015-10-20 | 2016-01-06 | 魅族科技(中国)有限公司 | Air navigation aid, guider and mobile terminal |
-
2016
- 2016-08-31 CN CN201610794146.7A patent/CN106441343B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101118162A (en) * | 2007-09-18 | 2008-02-06 | 倚天资讯股份有限公司 | System of realistic navigation combining landmark information, user interface and method |
CN102200448A (en) * | 2011-03-04 | 2011-09-28 | 鸿富锦精密工业(深圳)有限公司 | Positioning and navigation device |
CN102519478A (en) * | 2011-11-16 | 2012-06-27 | 深圳市凯立德科技股份有限公司 | Streetscape destination guiding method and device |
EP2889581A1 (en) * | 2012-09-20 | 2015-07-01 | Huawei Device Co., Ltd. | Navigation terminal, navigation method and remote navigation service system |
CN103105174A (en) * | 2013-01-29 | 2013-05-15 | 四川长虹佳华信息产品有限责任公司 | AR (augmented reality)-based vehicle-mounted live-action safe navigation method |
CN103134499A (en) * | 2013-02-06 | 2013-06-05 | 腾讯科技(深圳)有限公司 | Navigation method and navigation device |
CN104515529A (en) * | 2013-09-27 | 2015-04-15 | 高德软件有限公司 | Real-scenery navigation method and navigation equipment |
CN103674016A (en) * | 2013-12-16 | 2014-03-26 | 广东步步高电子工业有限公司 | Walking guide system based on mobile terminal and implementation method of walking guide system |
CN104850563A (en) * | 2014-02-18 | 2015-08-19 | 歌乐株式会社 | Destination image comparison retrieval device, destination image comparison retrieval system and destination image comparison retrieval method |
CN104966065A (en) * | 2015-06-23 | 2015-10-07 | 电子科技大学 | Target recognition method and device |
Also Published As
Publication number | Publication date |
---|---|
CN106441343A (en) | 2017-02-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106441343B (en) | Street view navigation method based on character recognition | |
JP5901779B2 (en) | How to move data from image database map service into assist system | |
CN106844376B (en) | Method and device for recommending interest points | |
US7733244B2 (en) | Navigation system | |
EP3673407A1 (en) | Automatic occlusion detection in road network data | |
US8255150B2 (en) | Dynamic destination map display for navigation system | |
US20100305842A1 (en) | METHOD AND APPARATUS TO FILTER AND DISPLAY ONLY POIs CLOSEST TO A ROUTE | |
US20190287398A1 (en) | Dynamic natural guidance | |
US20080040024A1 (en) | Method and apparatus of displaying three-dimensional arrival screen for navigation system | |
US20090198443A1 (en) | In-vehicle navigation device and parking space guiding method | |
US9383211B2 (en) | Navigation system and method for displaying map on navigation system | |
CN101910792A (en) | Navigation system | |
US11656090B2 (en) | Method and system for generating navigation data for a geographical location | |
TW200848703A (en) | Navigation assistance using camera | |
CN105865464A (en) | Method and apparatus for searching interest points surrounding path | |
US20110288763A1 (en) | Method and apparatus for displaying three-dimensional route guidance | |
CN107209021B (en) | System and method for visual relevance ranking of navigation maps | |
US10578449B2 (en) | Waypoint navigator | |
EP4089370A1 (en) | Method and device for verifying a current location and orientation of a user using landmarks | |
JP4923692B2 (en) | Route guidance device | |
US11054269B2 (en) | Providing navigation directions | |
JP2007322283A (en) | Drawing system | |
WO2007088915A1 (en) | Route guidance device, route guidance method, route guidance program, and recording medium | |
US20210364312A1 (en) | Routes on Digital Maps with Interactive Turn Graphics | |
JP5460252B2 (en) | Navigation device and navigation method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |