CN107958451A - Vision high accuracy map production method and device - Google Patents
Vision high accuracy map production method and device Download PDFInfo
- Publication number
- CN107958451A CN107958451A CN201711444384.6A CN201711444384A CN107958451A CN 107958451 A CN107958451 A CN 107958451A CN 201711444384 A CN201711444384 A CN 201711444384A CN 107958451 A CN107958451 A CN 107958451A
- Authority
- CN
- China
- Prior art keywords
- image
- high accuracy
- characteristic point
- information
- accuracy map
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration by the use of more than one image, e.g. averaging, subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Remote Sensing (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Processing Or Creating Images (AREA)
Abstract
A kind of vision high accuracy map production method and device, method include, and obtain image information, and extract image characteristic point；Image procossing is carried out to described image, to obtain the corresponding positional information of the characteristic point；Traffic information deep learning is carried out to described image, to obtain road information；The positional information is merged with the road information, to obtain high-precision map, so as to effectively reduce the cost of vision high accuracy cartography, improves the renewal speed of vision high accuracy map.
Description
Technical field
The present invention relates to technical field of image processing, and in particular to a kind of vision high accuracy map production method, one kind regard
Feel high-precision map manufacturing system, a kind of computer-readable recording medium and a kind of vision high accuracy map producing device.
Background technology
In order to obtain high-precision map, the collecting vehicle pair in correlation technique usually by being provided with laser radar or camera
Road conditions are acquired, then the image collected is collected to the drafting for carrying out map.But correlation technique there are the problem of be to be
Get the map of degree of precision, it is necessary to using higher acquisition capacity image acquisition device, therefore high-precision map is fabricated to
This height, and in order to be drawn to map, it is necessary to frequently make collecting vehicle be acquired activity, but still can not meet that nobody drives
Sail the road condition updating speed needed for technology.Therefore, correlation technique needs to improve.
The content of the invention
The application provides a kind of vision high accuracy map production method, be capable of effectively save high-precision mapping into
This, improves the renewal speed of high-precision map.
According in a first aspect, provide a kind of vision high accuracy map production method in a kind of embodiment, comprise the following steps：
Image information is obtained, and extracts image characteristic point；Image procossing is carried out to described image, to obtain the corresponding position of the characteristic point
Confidence ceases；Traffic information deep learning is carried out to described image, to obtain road information；To the positional information and the road
Information is merged, to obtain high-precision map.
Further, carrying out image procossing to described image includes：Described image characteristic point is matched；To progress
Characteristic point after matching somebody with somebody optimizes processing, to obtain the corresponding positional information of the characteristic point.
Further, subsection optimization processing is carried out to the characteristic point after matching.
According to second aspect, a kind of computer-readable recording medium, including program, described program are provided in a kind of embodiment
It can be executed by processor to realize the vision high accuracy map production method.
According to the third aspect, a kind of vision high accuracy map manufacturing system, including memory, place are provided in a kind of embodiment
Manage device and be stored in the computer program that can be run on the memory and on the processor, described in the processor execution
During computer program, the vision high accuracy map production method is realized.
According to fourth aspect, a kind of vision high accuracy map producing device is provided in a kind of embodiment, including：Image acquisition
Unit, for obtaining image information, and extracts image characteristic point；Image processing unit, for being carried out to described image at image
Reason, to obtain the corresponding positional information of the characteristic point；Image study unit, for carrying out traffic information depth to described image
Study, to obtain road information；Information fusion unit, for being merged to the positional information with the road information, with
Obtain high-precision map.
Further, described image processing unit is additionally operable to：Described image characteristic point is matched；After matching
Characteristic point optimize processing, to obtain the corresponding positional information of the characteristic point.
Further, described image processing unit is additionally operable to：Subsection optimization processing is carried out to the characteristic point after matching.
According to fourth aspect, a kind of vision high accuracy map manufacturing system is provided in a kind of embodiment, including described in realization
Vision high accuracy map producing device.
According to the vision high accuracy map production method of above-described embodiment, vision high accuracy cartography can be effectively reduced
Cost, improve vision high accuracy map renewal speed.
Brief description of the drawings
Fig. 1 is the flow chart according to the vision high accuracy map production method of the embodiment of the present invention；
Fig. 2 is the schematic diagram according to the vision high accuracy map production method of the embodiment of the present invention；
Fig. 3 is to handle schematic diagram according to the subsection optimization of the vision high accuracy map production method of the embodiment of the present invention；
Fig. 4 is the block diagram according to the vision high accuracy map producing device of the embodiment of the present invention.
Embodiment
The present invention is described in further detail below by embodiment combination attached drawing.Wherein different embodiments
Middle similar component employs associated similar element numbers.In the following embodiments, many detailed descriptions be in order to
The application is better understood.However, those skilled in the art can be without lifting an eyebrow recognize, which part feature
It is dispensed, or can be substituted by other elements, material, method in varied situations.In some cases, this Shen
Please relevant certain operations not in the description show or describe, this is the core in order to avoid the application by mistake
More descriptions are flooded, and to those skilled in the art, be described in detail these relevant operations be not it is necessary, they
The general technology knowledge of description and this area in specification can completely understand relevant operation.
In addition, feature described in this description, operation or feature can combine to form respectively in any suitable way
Kind embodiment.Meanwhile each step in method description or action can also can be aobvious and easy according to those skilled in the art institute
The mode carry out order exchange or adjustment seen.Therefore, the various orders in specification and drawings are intended merely to clearly describe a certain
A embodiment, is not meant to be necessary order, wherein some sequentially must comply with unless otherwise indicated.
SFM (Structure From Motion, exercise recovery structure) technologies are because its operand is larger, time-consuming at present
The characteristics of long, be mainly used in offline 3D and rebuild, also rarely have and applied in extensive map structuring.Based on this, apply
People devises a kind of vision high accuracy map production method, can realize SFM beyond the clouds when the present invention is conceived, and protects
Efficiency is greatly improved while demonstrate,proving performance, is truly realized the low delay structure of high-precision map.
Fig. 1 is the flow chart according to the vision high accuracy map production method of the embodiment of the present invention.As shown in Figure 1, this hair
The vision high accuracy map production method of bright embodiment comprises the following steps：
S1：Image information is obtained, and extracts image characteristic point.
It should be noted that image information can be the two dimensional image that image collecting device is got, wherein, image collector
It can be consumer level camera to put.Specifically, image collecting device may be provided on any one automobile, i.e. every automobile can be into
The image collected is simultaneously uploaded to high in the clouds by row Image Acquisition, to extract image characteristic point.
That is, Image Acquisition is carried out by camera, and the image to collecting carries out feature extraction, i.e., by image
Information changes into characteristic point information, so as to avoid a large amount of computings that the operation of pixel scale is brought.Wherein, can be by parallel
The mode of processing extracts image characteristic point.
S2：Image procossing is carried out to image, to obtain the corresponding positional information of characteristic point.
According to one embodiment of present invention, carrying out image procossing to image includes：Image characteristic point is matched, and
Processing is optimized to the characteristic point after matching, to obtain the corresponding positional information of characteristic point.
It should also be noted that, GPS device is further included in embodiments of the present invention, for obtaining current location longitude and latitude position
Confidence ceases.
Specifically, the corresponding GPS position information of picture is obtained, and obtains the history image in the region, is believed according to characteristic point
Breath is matched, so as to obtain the positional information of new characteristic point, constraints, and new feature are used as by the use of GPS information
The positional information of point, optimizes processing, to obtain the corresponding positional information of this feature point.
Wherein, the positional information of characteristic point can be 3D positional informations, and optimization processing can be BA (BundleAdjustment)
Optimization operation, so as to make the positional information of characteristic point more accurate.
Further, subsection optimization processing can be carried out to the characteristic point after matching to obtain the corresponding position of characteristic point
Information.
That is, since BA optimization operations are time-consuming longer, as figure amount increase operand can increase by geometric progression, because
Large-scale BA, can be optimized the BA optimization operations that operation is cut into many segments, be distributed to independent by this in the present embodiment
Once global optimization is carried out on distributed node, after the completion of concurrent operation again, so that significant increase while performance is ensured
Operation efficiency.
It should be noted that high in the clouds is the distributed processing network being made of the stronger processing node of disposal ability, so that
Being capable of parallel processing characteristic point.Wherein, the distributed system in high in the clouds has very high autgmentability and fault-tolerant ability, that is,
Say, even if any one node machine of delaying will not influence the correct operation of whole system in high in the clouds.
Specifically, as shown in figure 3, the characteristic point collected and GPS position information packing are uploaded to high in the clouds by acquisition terminal,
The GPS position information that high in the clouds is carried according to characteristic point, polymerize characteristic point, and the GPS position information after polymerization is sent into
Same processing node, and then part BA operations are performed to be optimized to characteristic point, wherein, polymerization scope is not more than 100m.
Further, Global B A operations are carried out to local BA operating results after the completion of local BA operations, it is large range of to optimize
Figure point precision.Wherein, in a big way no more than 1km, and Global B A operations may be provided at map without frequent updating and cloud system
Carried out when load is relatively low, for example, night, base portion map do not have large area more news etc., so as to ensure cloud system
The operation of efficient stable.
S3：Traffic information deep learning is carried out to image, to obtain road information.
It should be noted that the process that traffic information deep learning is carried out to image refers to for the traffic in detection pictorial information
Show the semantic informations such as board and traffic lights, and deep learning is carried out to semantic information, so as to obtain the corresponding road of picture
Information.
S4：Positional information is merged with road information, to obtain high-precision map.
That is, the corresponding positional information of characteristic point is corresponded with road information, so as to obtain this
The high-precision cartographic information of position correspondence.
A specific embodiment according to the present invention, as shown in Fig. 2, image collecting device and GPS gathers device can be set
Put on any one automobile, automobile in the process of moving carries out Image Acquisition and GPS position information collection, and will collect
Image and the corresponding GPS position information of image are sent to high in the clouds, and high in the clouds obtains image information, on the one hand extracts characteristics of image
Point, Feature Points Matching is carried out according to the corresponding GPS position information of image, then using GPS position information as constraints to image
Characteristic point carries out BA optimization operations, and then obtains the 3D positional informations of characteristic point, traffic information mark in another aspect detection image
Know, for example, traffic indication board and traffic light signal, and deep learning is carried out to traffic information mark in image, so as to obtain road
Information, 3D positional informations is corresponded with road information, so as to obtain high-precision map.
Since the embodiment of the present invention can use the image collecting device of consumer level, so as to effectively reduce map system
Make cost, and since image collecting device can be installed on every automobile, as long as so that any one road has an automobile
Pass through, you can the road is updated, the map rejuvenation of upper frequency can be carried out using section to high frequency, so as to full
The map rejuvenation demand of sufficient automatic driving vehicle.
In conclusion vision high accuracy map production method according to embodiments of the present invention, by obtaining image information, and
Image characteristic point is extracted, image procossing is carried out to image, to obtain the corresponding positional information of characteristic point, traffic letter is carried out to image
Deep learning is ceased, to obtain road information, positional information is merged with road information, to obtain high-precision map, so that
The cost of vision high accuracy cartography can be effectively reduced, improves the renewal speed of vision high accuracy map.
The embodiment of the present invention also proposed a kind of computer-readable recording medium, including program, and program can be by processor
Perform to realize vision high accuracy map production method.
Computer-readable recording medium according to embodiments of the present invention, by realizing vision high accuracy map production method,
The cost of vision high accuracy cartography can be effectively reduced, improves the renewal speed of vision high accuracy map.
The embodiment of the present invention also proposed a kind of vision high accuracy map manufacturing system, including memory, processor and deposit
The computer program that can be run on a memory and on a processor is stored up, when processor performs computer program, realizes vision height
Precision cartography method.
Vision high accuracy map manufacturing system according to embodiments of the present invention, by realizing vision high accuracy cartography side
Method, can effectively reduce the cost of vision high accuracy cartography, improve the renewal speed of vision high accuracy map.
A kind of embodiment corresponding, of the invention with the vision high accuracy map production method of above-mentioned several embodiments offers
Additionally provide vision high accuracy map producing device, due to vision high accuracy map producing device provided in an embodiment of the present invention with
The vision high accuracy map production method that above-mentioned several embodiments provide is corresponding, therefore in foregoing visual high accuracy cartography
The embodiment of method is also applied for vision high accuracy map producing device provided in this embodiment, no longer retouches in the present embodiment
State.
Fig. 4 is the vision high accuracy map producing device according to the embodiment of the present invention.As shown in figure 3, the embodiment of the present invention
Vision high accuracy map producing device, including：Image acquisition unit 10, image processing unit 20,30 and of image study unit
Information fusion unit 40.
Wherein, image acquisition unit 10 is used to obtain image information, and extracts image characteristic point；Image processing unit 20 is used
In carrying out image procossing to image, to obtain the corresponding positional information of characteristic point；Image study unit 30 is used to carry out image
Traffic information deep learning, to obtain road information；Information fusion unit 40 is used to melt positional information and road information
Close, to obtain high-precision map.
According to one embodiment of present invention, image processing unit is additionally operable to：Image characteristic point is matched；To carrying out
Characteristic point after matching optimizes processing, to obtain the corresponding positional information of characteristic point.
According to one embodiment of present invention, image processing unit is additionally operable to：Characteristic point after matching is divided
Section optimization processing.
In conclusion vision high accuracy map producing device according to embodiments of the present invention, is obtained by image acquisition unit
Image information is taken, and extracts image characteristic point, image processing unit carries out image image procossing, corresponding to obtain characteristic point
Positional information, image study unit carries out traffic information deep learning to image, to obtain road information, information fusion unit pair
Positional information is merged with road information, to obtain high-precision map, so as to effectively reduce vision high accuracy map system
The cost of work, improves the renewal speed of vision high accuracy map.
It will be understood by those skilled in the art that all or part of function of various methods can pass through in the above embodiment
The mode of hardware is realized, can also be realized by way of computer program.When all or part of function in the above embodiment
When being realized by way of computer program, which can be stored in a computer-readable recording medium, and storage medium can
With including：Read-only storage, random access memory, disk, CD, hard disk etc., it is above-mentioned to realize to perform the program by computer
Function.For example, by program storage in the memory of equipment, memory Program is performed when passing through processor, you can in realization
State all or part of function.In addition, when in the above embodiment all or part of function realized by way of computer program
When, which can also be stored in the storage mediums such as server, another computer, disk, CD, flash disk or mobile hard disk
In, by download or copying and saving into the memory of local device, or version updating is carried out to the system of local device, when logical
When crossing the program in processor execution memory, you can realize all or part of function in the above embodiment.
Use above specific case is illustrated the present invention, is only intended to help and understands the present invention, not limiting
The system present invention.For those skilled in the art, according to the thought of the present invention, can also make some simple
Deduce, deform or replace.
Claims (9)
1. a kind of vision high accuracy map production method, it is characterised in that comprise the following steps：
Image information is obtained, and extracts image characteristic point；
Image procossing is carried out to described image, to obtain the corresponding positional information of the characteristic point；
Traffic information deep learning is carried out to described image, to obtain road information；
The positional information is merged with the road information, to obtain high-precision map.
2. vision high accuracy map production method as claimed in claim 1, it is characterised in that carried out to described image at image
Reason includes：
Described image characteristic point is matched；
Processing is optimized to the characteristic point after matching, to obtain the corresponding positional information of the characteristic point.
3. vision high accuracy map production method as claimed in claim 2, it is characterised in that to the characteristic point after matching
Carry out subsection optimization processing.
4. a kind of computer-readable recording medium, it is characterised in that including program, described program can be executed by processor with reality
The now vision high accuracy map production method as any one of claim 1-3.
5. a kind of vision high accuracy map manufacturing system, it is characterised in that including memory, processor and be stored in the storage
On device and the computer program that can run on the processor, when the processor performs the computer program, realize such as
Vision high accuracy map production method any one of claim 1-3.
A kind of 6. vision high accuracy map producing device, it is characterised in that including：
Image acquisition unit, for obtaining image information, and extracts image characteristic point；
Image processing unit, for carrying out image procossing to described image, to obtain the corresponding positional information of the characteristic point；
Image study unit, for carrying out traffic information deep learning to described image, to obtain road information；
Information fusion unit, for being merged to the positional information with the road information, to obtain high-precision map.
7. vision high accuracy map producing device as claimed in claim 6, it is characterised in that described image processing unit is also used
In：
Described image characteristic point is matched；
Processing is optimized to the characteristic point after matching, to obtain the corresponding positional information of the characteristic point.
8. vision high accuracy map producing device as claimed in claim 7, it is characterised in that described image processing unit is also used
In：Subsection optimization processing is carried out to the characteristic point after matching.
9. a kind of vision high accuracy map manufacturing system, it is characterised in that including realizing as any one of claim 6-8
Vision high accuracy map producing device.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711444384.6A CN107958451A (en) | 2017-12-27 | 2017-12-27 | Vision high accuracy map production method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711444384.6A CN107958451A (en) | 2017-12-27 | 2017-12-27 | Vision high accuracy map production method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107958451A true CN107958451A (en) | 2018-04-24 |
Family
ID=61957059
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711444384.6A Pending CN107958451A (en) | 2017-12-27 | 2017-12-27 | Vision high accuracy map production method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107958451A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109189872A (en) * | 2018-08-13 | 2019-01-11 | 武汉中海庭数据技术有限公司 | Accurately diagram data verifies device and method |
| CN109515439A (en) * | 2018-11-13 | 2019-03-26 | 北京四维图新科技股份有限公司 | Automatic Pilot control method, device, system and storage medium |
| CN110060343A (en) * | 2019-04-24 | 2019-07-26 | 百度在线网络技术（北京）有限公司 | Map constructing method and system, server, computer-readable medium |
| US10390003B1 (en) | 2016-08-29 | 2019-08-20 | Perceptln Shenzhen Limited | Visual-inertial positional awareness for autonomous and non-autonomous device |
| CN110361016A (en) * | 2019-07-11 | 2019-10-22 | 浙江吉利汽车研究院有限公司 | One kind building drawing method and builds drawing system |
| CN112434119A (en) * | 2020-11-13 | 2021-03-02 | 武汉中海庭数据技术有限公司 | High-precision map production device based on heterogeneous data fusion |
| US11328158B2 (en) | 2016-08-29 | 2022-05-10 | Trifo, Inc. | Visual-inertial positional awareness for autonomous and non-autonomous tracking |
| US11501527B2 (en) | 2016-08-29 | 2022-11-15 | Trifo, Inc. | Visual-inertial positional awareness for autonomous and non-autonomous tracking |
| US11774983B1 (en) | 2019-01-02 | 2023-10-03 | Trifo, Inc. | Autonomous platform guidance systems with unknown environment mapping |
| US11842500B2 (en) | 2016-08-29 | 2023-12-12 | Trifo, Inc. | Fault-tolerance to provide robust tracking for autonomous and non-autonomous positional awareness |
| US11953910B2 (en) | 2016-08-29 | 2024-04-09 | Trifo, Inc. | Autonomous platform guidance systems with task planning and obstacle avoidance |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104317876A (en) * | 2014-10-21 | 2015-01-28 | 百度在线网络技术（北京）有限公司 | Road network vector data generation method and device |
| CN105260988A (en) * | 2015-09-09 | 2016-01-20 | 百度在线网络技术（北京）有限公司 | High-precision map data processing method and high-precision map data processing device |
| CN105674993A (en) * | 2016-01-15 | 2016-06-15 | 武汉光庭科技有限公司 | Binocular camera-based high-precision visual sense positioning map generation system and method |
| CN106441319A (en) * | 2016-09-23 | 2017-02-22 | 中国科学院合肥物质科学研究院 | System and method for generating lane-level navigation map of unmanned vehicle |
| CN106525057A (en) * | 2016-10-26 | 2017-03-22 | 陈曦 | Generation system for high-precision road map |
| CN106969764A (en) * | 2016-01-13 | 2017-07-21 | 北京四维图新科技股份有限公司 | A kind of road matching method, device and vehicular map acquisition system |
| CN107229690A (en) * | 2017-05-19 | 2017-10-03 | 广州中国科学院软件应用技术研究所 | Dynamic High-accuracy map datum processing system and method based on trackside sensor |
| CN107368890A (en) * | 2016-05-11 | 2017-11-21 | Tcl集团股份有限公司 | A kind of road condition analyzing method and system based on deep learning centered on vision |
-
2017
- 2017-12-27 CN CN201711444384.6A patent/CN107958451A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104317876A (en) * | 2014-10-21 | 2015-01-28 | 百度在线网络技术（北京）有限公司 | Road network vector data generation method and device |
| CN105260988A (en) * | 2015-09-09 | 2016-01-20 | 百度在线网络技术（北京）有限公司 | High-precision map data processing method and high-precision map data processing device |
| CN106969764A (en) * | 2016-01-13 | 2017-07-21 | 北京四维图新科技股份有限公司 | A kind of road matching method, device and vehicular map acquisition system |
| CN105674993A (en) * | 2016-01-15 | 2016-06-15 | 武汉光庭科技有限公司 | Binocular camera-based high-precision visual sense positioning map generation system and method |
| CN107368890A (en) * | 2016-05-11 | 2017-11-21 | Tcl集团股份有限公司 | A kind of road condition analyzing method and system based on deep learning centered on vision |
| CN106441319A (en) * | 2016-09-23 | 2017-02-22 | 中国科学院合肥物质科学研究院 | System and method for generating lane-level navigation map of unmanned vehicle |
| CN106525057A (en) * | 2016-10-26 | 2017-03-22 | 陈曦 | Generation system for high-precision road map |
| CN107229690A (en) * | 2017-05-19 | 2017-10-03 | 广州中国科学院软件应用技术研究所 | Dynamic High-accuracy map datum processing system and method based on trackside sensor |
Non-Patent Citations (1)
| Title |
|---|
| 徐硕 等: "《汽车实用技术》", 31 December 2015 * |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11501527B2 (en) | 2016-08-29 | 2022-11-15 | Trifo, Inc. | Visual-inertial positional awareness for autonomous and non-autonomous tracking |
| US11953910B2 (en) | 2016-08-29 | 2024-04-09 | Trifo, Inc. | Autonomous platform guidance systems with task planning and obstacle avoidance |
| US10390003B1 (en) | 2016-08-29 | 2019-08-20 | Perceptln Shenzhen Limited | Visual-inertial positional awareness for autonomous and non-autonomous device |
| US11900536B2 (en) | 2016-08-29 | 2024-02-13 | Trifo, Inc. | Visual-inertial positional awareness for autonomous and non-autonomous tracking |
| US11842500B2 (en) | 2016-08-29 | 2023-12-12 | Trifo, Inc. | Fault-tolerance to provide robust tracking for autonomous and non-autonomous positional awareness |
| US11328158B2 (en) | 2016-08-29 | 2022-05-10 | Trifo, Inc. | Visual-inertial positional awareness for autonomous and non-autonomous tracking |
| CN109189872B (en) * | 2018-08-13 | 2021-06-04 | 武汉中海庭数据技术有限公司 | High-precision map data verification device and method |
| CN109189872A (en) * | 2018-08-13 | 2019-01-11 | 武汉中海庭数据技术有限公司 | Accurately diagram data verifies device and method |
| CN109515439A (en) * | 2018-11-13 | 2019-03-26 | 北京四维图新科技股份有限公司 | Automatic Pilot control method, device, system and storage medium |
| US11774983B1 (en) | 2019-01-02 | 2023-10-03 | Trifo, Inc. | Autonomous platform guidance systems with unknown environment mapping |
| CN110060343B (en) * | 2019-04-24 | 2023-06-20 | 阿波罗智能技术(北京)有限公司 | Map construction method and system, server and computer readable medium |
| CN110060343A (en) * | 2019-04-24 | 2019-07-26 | 百度在线网络技术（北京）有限公司 | Map constructing method and system, server, computer-readable medium |
| CN110361016B (en) * | 2019-07-11 | 2021-03-26 | 浙江吉利汽车研究院有限公司 | Picture construction method and system |
| CN110361016A (en) * | 2019-07-11 | 2019-10-22 | 浙江吉利汽车研究院有限公司 | One kind building drawing method and builds drawing system |
| CN112434119A (en) * | 2020-11-13 | 2021-03-02 | 武汉中海庭数据技术有限公司 | High-precision map production device based on heterogeneous data fusion |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107958451A (en) | Vision high accuracy map production method and device | |
| KR102338270B1 (en) | Method, apparatus, and computer readable storage medium for updating electronic map | |
| US9733094B2 (en) | Hybrid road network and grid based spatial-temporal indexing under missing road links | |
| CN108763287B (en) | Construction method of large-scale passable regional driving map and unmanned application method thereof | |
| CN111695488B (en) | Method, device, equipment and storage medium for identifying interest surface | |
| CN111582189B (en) | Traffic signal lamp identification method and device, vehicle-mounted control terminal and motor vehicle | |
| US10838988B2 (en) | System and method for efficient geospatial indexing | |
| WO2021003487A1 (en) | Training data generation for dynamic objects using high definition map data | |
| US11257200B1 (en) | Computationally efficient distance-based score approximations | |
| CN111508258A (en) | Positioning method and device | |
| JP6789334B2 (en) | Electronic map display method and equipment | |
| US20170336215A1 (en) | Classifying entities in digital maps using discrete non-trace positioning data | |
| US11385063B1 (en) | Computationally efficient distance-based score approximations | |
| CN113673400A (en) | Real scene three-dimensional semantic reconstruction method and device based on deep learning and storage medium | |
| CN112269849A (en) | Three-dimensional map display method, system, electronic equipment and storage medium | |
| CN103712628A (en) | Navigation path drawing method and terminal | |
| CN114295119A (en) | Map construction method and device | |
| CN114820679A (en) | Image annotation method and device, electronic equipment and storage medium | |
| CN102968472A (en) | Method and system of data caching for GIS (geographic information system) | |
| CN116222539A (en) | High-precision map data differentiated updating method and system | |
| US10896533B2 (en) | Automated identification of geographic site boundaries | |
| CN116465394B (en) | Road network structure generation method and device based on vehicle track data | |
| CN116718181B (en) | Map generation method, map generation device, electronic equipment and storage medium | |
| KR102592628B1 (en) | Apparatus and method for determining branching point | |
| CN117830433A (en) | Camera external parameter calibration input image processing method, device, equipment and medium |
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: 20180424 |
|
| RJ01 | Rejection of invention patent application after publication |