CN109934920A - High-precision three-dimensional point cloud map constructing method based on low-cost equipment - Google Patents
High-precision three-dimensional point cloud map constructing method based on low-cost equipment Download PDFInfo
- Publication number
- CN109934920A CN109934920A CN201910417580.7A CN201910417580A CN109934920A CN 109934920 A CN109934920 A CN 109934920A CN 201910417580 A CN201910417580 A CN 201910417580A CN 109934920 A CN109934920 A CN 109934920A
- Authority
- CN
- China
- Prior art keywords
- point cloud
- frame
- acquisition unit
- point
- data
- 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.)
- Granted
Links
Abstract
The present invention is directed to automatic Pilot scene, high-precision three-dimensional point cloud map constructing method based on low-cost equipment is provided, it is successively to execute point cloud pretreatment, interframe registration, screening key frame, fusion gps and imu data, key frame pose optimization five steps of building on inexpensive three-dimensional point cloud map structuring platform, generates three-dimensional point cloud map.Platform is made of laser point cloud acquisition unit, imu data acquisition unit, gps data acquisition unit and computing platform, and wherein laser point cloud acquisition unit uses 16 lines or 32 line laser radars;Gps data acquisition unit uses the inexpensive gps of grade of errors rice, provides the latitude and longitude information of low frequency for system;Imu data acquisition unit provides the acceleration and angular speed information of high frequency for system.The present invention using low cost build figure equipment cooperate it is completely new build nomography, under the premise of meeting equal accuracy, save the construction cost of three-dimensional point cloud map.
Description
Technical field
The invention belongs to automatic Pilot technical field, it is related to the laser radar system and method for map making, specifically
It is the high-precision three-dimensional point cloud map constructing method based on low-cost equipment for automatic Pilot scene.
Background technique
In automatic Pilot field, vehicle needs the moment to obtain itself position and posture, and based on this to following
Behavior make decisions (acceleration, deceleration, turn to).Current vehicle mainly passes through two methods and obtains current location.
The first, calculates the current longitude and latitude of vehicle using the signal of navigation satellite by three-point fox method, then exists
Current position is matched in two-dimensional map comprising latitude and longitude information, meanwhile, vehicle body appearance is calculated according to adjacent position information
State.The time that this method occurs is early, and by the improvement of many years, positioning accuracy can be increased to cm grades.But this method is to leading
The signal dependence of boat satellite is stronger, in the high block that signal is easily blocked, boulevard, and underground garage, sky parking, positioning
Precision is often greatly reduced, and causes positioning mistake.
Second, the three-dimensional point cloud of vehicle periphery is gone out by high frequency lasers radar scanning, the point then obtained using scanning
Cloud matches current location and the direction of vehicle in the good three-dimensional point cloud map of pre-production.This method uses three-dimensional space
The point of middle substantial amounts is matched, and matching precision can easily reach cm grades.Simultaneously as the three-dimensional character of point cloud, vehicle body
The point cloud that can directly be obtained by Current Scan of posture information obtained with map point cloud matching, do not need to be scanned into using adjacent
Row operation show that attitude accuracy is higher than method one.
Existing high-precision three-dimensional point cloud map constructing method uses sensing dedicated vehicle-mounted or taking human as carrier mostly
Device platform acquires laser point cloud (while acquiring imu and high-precision RTK data), is then built offline using the cooperation of professional computing platform
Nomography calculates a cloud map.It is this to build drawing method, largely used professional equipment, generally include with base station RTK and
High line number laser radar (64 lines, 128 lines), professional color image acquisition system and professional computing platform.It is with high costs, one
Secondary property investment is big, plant maintenance difficulty is larger be faced when constructing high-precision dot cloud map in existing automatic Pilot field it is main
Problem.
Summary of the invention
Goal of the invention: in order to overcome the deficiencies in the prior art, the present invention is directed to automatic Pilot scene, provides and be based on
The high-precision three-dimensional point cloud map structuring scheme of low-cost equipment.
Technical solution: in order to solve the above technical problems, the high-precision three-dimensional point provided by the invention based on low-cost equipment
Cloud map constructing method is that point cloud pretreatment, interframe registration, sieve are successively executed on inexpensive three-dimensional point cloud map structuring platform
Key frame, fusion gps and imu data, key frame pose optimization five steps of building are selected, three-dimensional point cloud map is generated;
The low cost three-dimensional point cloud map structuring platform includes laser point cloud acquisition unit, imu data acquisition unit, gps number
According to acquisition unit and computing platform;The laser point cloud acquisition unit uses 16 lines or 32 line laser radars;The gps data are adopted
Collect the inexpensive gps that unit uses grade of errors rice, provides the latitude and longitude information of low frequency for system;The imu data acquisition is single
Member provides the acceleration and angular speed information of high frequency for system.
Specifically, the laser point cloud acquisition unit uses 32 line laser radars, with the frequency collection three-dimensional point cloud of 10Hz
Data provide point cloud data accurately containing timestamp for system;The unit is composition portion mostly important in whole system
Point.
Specifically, the imu data acquisition unit completes the zero shift rectifying after powering on and temperature-compensating, the unit by program
The frequency of the acceleration and angular speed information provided for system is 50Hz.
Specifically, the gps data acquisition unit is 4Hz, the longitude and latitude of low frequency for the frequency that system provides latitude and longitude information
Degree information and the imu data of high frequency carry out ekf and merge to obtain the laser radar track of the 50Hz containing timestamp and attitude data.
Specifically, the computing platform uses the PC platform of (SuSE) Linux OS, and map generates software and is based on PCL point cloud
Handle library, figure optimization tool library and ROS.
Building nomography, specific step is as follows:
1 > point cloud pretreatment: marking the ground point and non-ground points in current point cloud frame first, then gets the bid in non-ground points
Remember angle point peace millet cake out, rejects in point cloud data all the points in addition to ground point, except angle point and planar point.
2 > interframe registration: a cloud is carried out using by pretreated current point cloud frame and by pretreated previous frame point cloud
Registration, calculating come from previous frame point cloud data to this frame point cloud data, the transposed matrix and posture spin matrix of laser radar,
The first frame point cloud data received using system is starting point using consecutive frame transposed matrix and spin matrix, and cumulative consecutive points cloud frame obtains
To continuous point cloud map.
3 > screening key frame: using the first frame point cloud data that system receives as first key frame, as interframe is registrated
Progress, statistics present frame arrive previous keyframe Euclidean distance, when Euclidean distance be greater than set threshold value when, then by present frame
Labeled as key frame.
4 > fusion gps and imu data: band is gone out sometimes to time integral calculation first with the acceleration and angular speed of imu
Between the path point stabbed, merge gps path point using ekf method and path point that imu is integrated out, obtain fused path points
According to set.
5 > key frame pose optimization: the fusion rear path point data set obtained according to the timestamp of path point in step 4
Middle hunting time and immediate two path points of current point cloud key frame, under the hypothesis of linear uniform motion, using linear
Interpolation calculation goes out hypothesis pose of the key frame based on path point, assumes pose with this for convergent target, optimizes a upper pass
Transposed matrix and spin matrix of the key frame until each frame point cloud between current key frame.
In use, satellite navigation signals receiving device (grade of errors: rice) of the present invention using low cost, IMU(inertia are surveyed
Amount unit) and cost laser radar (16 lines, 32 lines) cooperate a kind of a set of offline figure scheme of building of novel Algorithm constitution.Algorithm
Pretreatment amendment is carried out to cloud first, then goes out local map using pretreated cloud, utilizes navigation letter later
Number and the geographical track correct local map that merges out of IMU in key frame, finally met by constrained optimization of key frame
The three-dimensional point cloud map of geographical track.
The utility model has the advantages that existing high-precision laser point cloud map constructing method establishes constraint using the high-precision track RTK,
Then optimized using this constraint and build the continuous point cloud data scanned during figure to be spliced into one accurately, completely
Laser point cloud map.Due to the error of laser radar itself, the three-dimensional structure of the point cloud data and real scene that scan is not
It is completely coincident (plane there are bumps, and straight line is distorted).The method for point cloud optimization of constraint is established to such error using the track RTK
Amendment it is poor, therefore existing drawing method of building both had depended on high-precision RTK equipment to provide correct profile constraints, it is also desirable to high
The laser radar of precision provides the surrounding three-dimensional scan data of low error, this makes the with high costs of whole system.
The present invention cooperates one kind is novel to build nomography using the figure equipment of building of low cost, can greatly save three-dimensional point cloud
Map builds figure cost, verifies identical cloud location algorithm through embodiment, under static conditions, builds figure side using what this patent proposed
The point cloud map that method generates, the point cloud Orientation on map precision phase that positioning accuracy is generated with existing high-precision dot cloud map constructing method
Together.(less than 50 KM/H) under the dynamic condition of city, positioned on the point cloud map that the two generates, positioning accuracy is identical.
Except it is above-described present invention solves the technical problem that, constitute technical solution technical characteristic and by these technologies
Outside advantage brought by the technical characteristic of scheme.To keep the object of the invention, technical scheme and beneficial effects clearer, below will
In conjunction with the attached drawing in the embodiment of the present invention, to other for including in the other technologies problem of the invention that can solve, technical solution
The advantages of technical characteristic and these technical characteristics are brought does apparent, complete description.
Detailed description of the invention
Fig. 1 is the hardware architecture diagram of the inexpensive three-dimensional point cloud map structuring platform in the embodiment of the present invention;
Fig. 2 is to build nomography flow chart performed by inexpensive three-dimensional point cloud map structuring platform.
Specific embodiment
Embodiment:
As shown in Figure 1, the present embodiment is for laser point cloud hardware group inexpensive provided by automatic Pilot scene map structuring
Conjunction scheme, use low cost satellite navigation signals receiving device (grade of errors: rice), IMU(Inertial Measurement Unit) and it is low at
This laser radar (16 lines, 32 lines).The hardware system is adopted by laser point cloud acquisition unit, imu data acquisition unit, gps data
Collect unit, four part of computing platform is constituted.
1 > laser point cloud acquisition unit uses 32 line laser radars, with the frequency collection three dimensional point cloud of 10Hz.This
Unit provides point cloud data accurately containing timestamp for system, is component part mostly important in whole system.
2 > imu data acquisition unit uses thousand yuan of grade low cost imu, completes the zero shift rectifying after powering on and temperature by program
Compensation.This unit provides the acceleration and angular speed information of high frequency (50Hz) for system, merges gps data by ekf and obtains
Laser radar motion profile and posture containing timestamp.
3 > gps data acquisition unit uses thousand yuan of grade low cost gps, grade of errors rice, data output frequencies 4Hz.This
Unit provides the latitude and longitude information of low frequency for system, and it is available containing having time to carry out ekf fusion by the imu data with high frequency
The laser radar track of the high frequency (50Hz) of stamp and attitude data.
4 > computing platform uses a dell notebook (i7-8750h processor, 16G memory), and operating system is
Ubuntu16.04, map generate software and are based on PCL points cloud processing library, figure optimization tool library and ROS.
As shown in Fig. 2, the laser point cloud map making hardware plan of the above-mentioned low cost of cooperation, generates with laser point cloud map
Algorithm composition is a set of to build figure scheme offline.Algorithm carries out pretreatment amendment to cloud first, then utilizes pretreated cloud
It is spliced into local map, the key frame in geographical track correct local map for utilizing navigation signal and IMU to merge out later, most
The three-dimensional point cloud map for meeting geographical track is obtained by constrained optimization of key frame eventually.
The software flow of building three-dimensional point cloud mainly includes five parts: point cloud pretreatment, interframe registration, screening key
Frame, gps and imu data fusion, the optimization of key frame pose.Wherein:
1 > point cloud pretreatment: marking the ground point and non-ground points in current point cloud frame first, then gets the bid in non-ground points
Remember angle point peace millet cake out, rejects in point cloud data all the points in addition to ground point, except angle point and planar point.
2 > interframe registration: a cloud is carried out using by pretreated current point cloud frame and by pretreated previous frame point cloud
Registration, calculating come from previous frame point cloud data to this frame point cloud data, the transposed matrix and posture spin matrix of laser radar,
The first frame point cloud data received using system is starting point using consecutive frame transposed matrix and spin matrix, and cumulative consecutive points cloud frame obtains
To continuous point cloud map.
3 > screening key frame: using the first frame point cloud data that system receives as first key frame, with interframe
The progress of registration, the Euclidean distance of statistics present frame to previous keyframe will then work as when Euclidean distance is greater than the threshold value of setting
Previous frame is labeled as key frame.
4 > gps and imu data fusion: band is gone out sometimes to time integral calculation first with the acceleration and angular speed of imu
Between the path point stabbed, merge gps path point using ekf method and path point that imu is integrated out, obtain fused path points
According to set.
The optimization of 5 > key frame pose: according to the timestamp of path point 4 > obtained fusion rear path point data set in seek
Time and immediate two path points of current point cloud key frame is looked for utilize linear interpolation under the hypothesis of linear uniform motion
Hypothesis pose of the key frame based on path point is calculated, assumes that pose for convergent target, optimizes a upper key frame with this
Until the transposed matrix and spin matrix of each frame between current key frame.
The pseudocode of process is as follows:
BEGIN
IF point cloud data reaches THEN
A. point cloud pretreatment is carried out
B. interframe is registrated
C. according to interframe registration as a result, present frame is spelled access point cloud map
The Euclidean distance of IF present frame and a upper key frame reaches threshold value THEN
Keyframe sequence is added in current point cloud
IF finds timestamp former and later two path point THEN nearest from current key frame
It obtains assuming position auto―control, optimization upper one using former and later two path points
A key frame until each frame between current key frame transposed matrix and
Spin matrix
END IF
END IF
END IF
END
It is demonstrated experimentally that identical cloud location algorithm, under static conditions, the point cloud for building drawing method generation that uses this patent to propose
Map, positioning accuracy are identical as the point cloud Orientation on map precision that existing high-precision dot cloud map constructing method generates.City dynamic
Under the conditions of (less than 50 KM/H), the two generate point cloud map on positioned, positioning accuracy is identical.Scheme uses flat
Platform Cost comparisons are as follows:
The present invention is directed to automatic Pilot scene, builds figure for low cost and provides a kind of completely new thinking and method, specific implementation should
There are many method and approach of technical solution, and described embodiments are some of the embodiments of the present invention, rather than whole implementation
Example.The component of embodiments of the present invention, which are generally described and illustrated herein in the accompanying drawings can with a variety of different configurations arranging and
Design.Therefore, claimed invention is not intended to limit to the detailed description of the embodiment of the present invention provided in attached drawing
Range, but be merely representative of selected embodiment of the invention.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without creative efforts, shall fall within the protection scope of the present invention.
Claims (6)
1. a kind of high-precision three-dimensional point cloud map constructing method based on low-cost equipment, it is characterised in that: inexpensive three-dimensional
Point cloud pretreatment is successively executed on point cloud map structuring platform, interframe registration, screening key frame, fusion gps and imu data, is closed
Key framing bit appearance optimizes construction step, generates three-dimensional point cloud map;
The low cost three-dimensional point cloud map structuring platform includes laser point cloud acquisition unit, imu data acquisition unit, gps number
According to acquisition unit and computing platform;The laser point cloud acquisition unit uses 16 lines or 32 line laser radars;The gps data are adopted
Collect the inexpensive gps that unit uses grade of errors rice, provides the latitude and longitude information of low frequency for system;The imu data acquisition is single
Member provides the acceleration and angular speed information of high frequency for system.
2. the high-precision three-dimensional point cloud map constructing method according to claim 1 based on low-cost equipment, feature exist
In: the laser point cloud acquisition unit is mentioned using 32 line laser radars with the frequency collection three dimensional point cloud of 10Hz for system
For accurately containing the point cloud data of timestamp.
3. the high-precision three-dimensional point cloud map constructing method according to claim 1 based on low-cost equipment, feature exist
Zero shift rectifying and temperature-compensating after the imu data acquisition unit is completed to power on by program, the unit are what system provided
The frequency of acceleration and angular speed information is 50Hz.
4. the high-precision three-dimensional point cloud map constructing method according to claim 1 based on low-cost equipment, feature exist
It for the frequency that system provides latitude and longitude information is 4Hz in the gps data acquisition unit, the latitude and longitude information of low frequency and high frequency
Imu data carry out ekf and merge to obtain the laser radar track of the 50Hz containing timestamp and attitude data.
5. the high-precision three-dimensional point cloud map constructing method according to claim 1 based on low-cost equipment, feature exist
In: the computing platform uses the PC platform of (SuSE) Linux OS, and map generates software and is based on PCL points cloud processing library, figure optimization
Tool storage room and ROS.
6. the high-precision three-dimensional point cloud map constructing method according to claim 1 based on low-cost equipment, feature exist
In the following steps are included:
Step 1, point cloud pretreatment: the ground point and non-ground points in current point cloud frame are marked first, then in non-ground points
Middle label angle of departure point and planar point reject in point cloud data all the points in addition to ground point, except angle point and planar point;
Step 2, interframe is registrated: carrying out a cloud using by pretreated current point cloud frame and by pretreated previous frame point cloud
Registration, calculating come from previous frame point cloud data to this frame point cloud data, the transposed matrix and posture spin matrix of laser radar,
The first frame point cloud data received using system is starting point using consecutive frame transposed matrix and spin matrix, and cumulative consecutive points cloud frame obtains
To continuous point cloud map;
Step 3, key frame is screened: using the first frame point cloud data that system receives as first key frame, as interframe is registrated
Progress, statistics present frame arrive previous keyframe Euclidean distance, when Euclidean distance be greater than set threshold value when, then by present frame
Labeled as key frame;
Step 4, band fusion gps and imu data: is gone out sometimes to time integral calculation first with the acceleration and angular speed of imu
Between the path point stabbed, merge gps path point using ekf method and path point that imu is integrated out, obtain fused path points
According to set;
Step 5, key frame pose optimizes: the fusion rear path point data set obtained according to the timestamp of path point in step 4
Middle hunting time and immediate two path points of current point cloud key frame, under the hypothesis of linear uniform motion, using linear
Interpolation calculation goes out hypothesis pose of the key frame based on path point, assumes pose with this for convergent target, optimizes a upper pass
Transposed matrix and spin matrix of the key frame until each frame point cloud between current key frame.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910417580.7A CN109934920B (en) | 2019-05-20 | 2019-05-20 | High-precision three-dimensional point cloud map constructing method based on low-cost equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910417580.7A CN109934920B (en) | 2019-05-20 | 2019-05-20 | High-precision three-dimensional point cloud map constructing method based on low-cost equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109934920A true CN109934920A (en) | 2019-06-25 |
CN109934920B CN109934920B (en) | 2019-08-09 |
Family
ID=66991380
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910417580.7A Active CN109934920B (en) | 2019-05-20 | 2019-05-20 | High-precision three-dimensional point cloud map constructing method based on low-cost equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109934920B (en) |
Cited By (25)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110262538A (en) * | 2019-07-01 | 2019-09-20 | 百度在线网络技术(北京)有限公司 | Map data collecting method, apparatus, equipment and storage medium |
CN110427027A (en) * | 2019-07-18 | 2019-11-08 | 浙江吉利汽车研究院有限公司 | Navigation routine generation method, device and automated driving system for automatic Pilot |
CN110441791A (en) * | 2019-08-14 | 2019-11-12 | 深圳无境智能机器人有限公司 | A kind of ground obstacle detection method based on the 2D laser radar that leans forward |
CN110827403A (en) * | 2019-11-04 | 2020-02-21 | 北京易控智驾科技有限公司 | Method and device for constructing three-dimensional point cloud map of mine |
CN110967020A (en) * | 2019-11-29 | 2020-04-07 | 畅加风行(苏州)智能科技有限公司 | Drawing and positioning simultaneously for port automatic driving |
CN111189449A (en) * | 2020-01-21 | 2020-05-22 | 杭州大数云智科技有限公司 | Robot map construction method |
CN111381248A (en) * | 2020-03-23 | 2020-07-07 | 湖南大学 | Obstacle detection method and system considering vehicle bump |
CN111429528A (en) * | 2020-04-07 | 2020-07-17 | 高深智图(广州)科技有限公司 | Large-scale distributed high-precision map data processing system |
CN111710040A (en) * | 2020-06-03 | 2020-09-25 | 纵目科技(上海)股份有限公司 | Method, system, terminal and storage medium for constructing high-precision map |
CN111710039A (en) * | 2020-06-03 | 2020-09-25 | 纵目科技(上海)股份有限公司 | Method, system, terminal and storage medium for constructing high-precision map |
CN111765886A (en) * | 2020-05-18 | 2020-10-13 | 浙江西贝虎特种车辆股份有限公司 | Multi-terminal collaborative forest crown lower landform mapping system and method |
CN112067007A (en) * | 2020-11-12 | 2020-12-11 | 湖北亿咖通科技有限公司 | Map generation method, computer storage medium, and electronic device |
CN112086010A (en) * | 2020-09-03 | 2020-12-15 | 中国第一汽车股份有限公司 | Map generation method, map generation device, map generation equipment and storage medium |
CN112204344A (en) * | 2019-08-30 | 2021-01-08 | 深圳市大疆创新科技有限公司 | Pose acquisition method and system and movable platform |
CN112767458A (en) * | 2020-11-13 | 2021-05-07 | 武汉中海庭数据技术有限公司 | Method and system for registering laser point cloud and image |
CN112799096A (en) * | 2021-04-08 | 2021-05-14 | 西南交通大学 | Map construction method based on low-cost vehicle-mounted two-dimensional laser radar |
WO2021103512A1 (en) * | 2019-11-26 | 2021-06-03 | Suzhou Zhijia Science & Technologies Co., Ltd. | Method and apparatus for generating electronic map |
CN113034566A (en) * | 2021-05-28 | 2021-06-25 | 湖北亿咖通科技有限公司 | High-precision map construction method and device, electronic equipment and storage medium |
WO2021232227A1 (en) * | 2020-05-19 | 2021-11-25 | 深圳市大疆创新科技有限公司 | Point cloud frame construction method, target detection method, ranging apparatus, movable platform, and storage medium |
CN113706676A (en) * | 2021-08-26 | 2021-11-26 | 京东鲲鹏(江苏)科技有限公司 | Model self-supervision training method and device for point cloud data |
CN113759369A (en) * | 2020-06-28 | 2021-12-07 | 北京京东乾石科技有限公司 | Image establishing method and device based on double multiline radar |
CN113819914A (en) * | 2020-06-19 | 2021-12-21 | 北京图森未来科技有限公司 | Map construction method and device |
CN114332232A (en) * | 2022-03-11 | 2022-04-12 | 中国人民解放军国防科技大学 | Smart phone indoor positioning method based on space point, line and surface feature hybrid modeling |
CN115267725A (en) * | 2022-09-27 | 2022-11-01 | 上海仙工智能科技有限公司 | Drawing establishing method and device based on single-line laser radar and storage medium |
CN115638787A (en) * | 2022-12-23 | 2023-01-24 | 安徽蔚来智驾科技有限公司 | Digital map generation method, computer readable storage medium and electronic device |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105702151A (en) * | 2016-03-31 | 2016-06-22 | 百度在线网络技术(北京)有限公司 | Indoor map constructing method and device |
CN106846467A (en) * | 2017-01-23 | 2017-06-13 | 阿依瓦(北京)技术有限公司 | Entity scene modeling method and system based on the optimization of each camera position |
CN108801276A (en) * | 2018-07-23 | 2018-11-13 | 奇瑞汽车股份有限公司 | Accurately drawing generating method and device |
CN109341706A (en) * | 2018-10-17 | 2019-02-15 | 张亮 | A kind of production method of the multiple features fusion map towards pilotless automobile |
CN109710724A (en) * | 2019-03-27 | 2019-05-03 | 深兰人工智能芯片研究院(江苏)有限公司 | A kind of method and apparatus of building point cloud map |
-
2019
- 2019-05-20 CN CN201910417580.7A patent/CN109934920B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105702151A (en) * | 2016-03-31 | 2016-06-22 | 百度在线网络技术(北京)有限公司 | Indoor map constructing method and device |
CN106846467A (en) * | 2017-01-23 | 2017-06-13 | 阿依瓦(北京)技术有限公司 | Entity scene modeling method and system based on the optimization of each camera position |
CN108801276A (en) * | 2018-07-23 | 2018-11-13 | 奇瑞汽车股份有限公司 | Accurately drawing generating method and device |
CN109341706A (en) * | 2018-10-17 | 2019-02-15 | 张亮 | A kind of production method of the multiple features fusion map towards pilotless automobile |
CN109710724A (en) * | 2019-03-27 | 2019-05-03 | 深兰人工智能芯片研究院(江苏)有限公司 | A kind of method and apparatus of building point cloud map |
Cited By (40)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110262538A (en) * | 2019-07-01 | 2019-09-20 | 百度在线网络技术(北京)有限公司 | Map data collecting method, apparatus, equipment and storage medium |
CN110262538B (en) * | 2019-07-01 | 2023-03-14 | 百度在线网络技术(北京)有限公司 | Map data acquisition method, device, equipment and storage medium |
CN110427027A (en) * | 2019-07-18 | 2019-11-08 | 浙江吉利汽车研究院有限公司 | Navigation routine generation method, device and automated driving system for automatic Pilot |
CN110427027B (en) * | 2019-07-18 | 2022-09-02 | 浙江吉利汽车研究院有限公司 | Navigation route generation method and device for automatic driving and automatic driving system |
CN110441791A (en) * | 2019-08-14 | 2019-11-12 | 深圳无境智能机器人有限公司 | A kind of ground obstacle detection method based on the 2D laser radar that leans forward |
CN112204344A (en) * | 2019-08-30 | 2021-01-08 | 深圳市大疆创新科技有限公司 | Pose acquisition method and system and movable platform |
WO2021035748A1 (en) * | 2019-08-30 | 2021-03-04 | 深圳市大疆创新科技有限公司 | Pose acquisition method, system, and mobile platform |
CN110827403A (en) * | 2019-11-04 | 2020-02-21 | 北京易控智驾科技有限公司 | Method and device for constructing three-dimensional point cloud map of mine |
CN110827403B (en) * | 2019-11-04 | 2023-08-25 | 北京易控智驾科技有限公司 | Construction method and device of mine three-dimensional point cloud map |
WO2021103512A1 (en) * | 2019-11-26 | 2021-06-03 | Suzhou Zhijia Science & Technologies Co., Ltd. | Method and apparatus for generating electronic map |
CN110967020A (en) * | 2019-11-29 | 2020-04-07 | 畅加风行(苏州)智能科技有限公司 | Drawing and positioning simultaneously for port automatic driving |
CN110967020B (en) * | 2019-11-29 | 2024-02-27 | 畅加风行(苏州)智能科技有限公司 | Simultaneous drawing and positioning method for port automatic driving |
CN111189449A (en) * | 2020-01-21 | 2020-05-22 | 杭州大数云智科技有限公司 | Robot map construction method |
CN111189449B (en) * | 2020-01-21 | 2023-04-25 | 杭州大数云智科技有限公司 | Robot map construction method |
CN111381248B (en) * | 2020-03-23 | 2023-06-09 | 湖南大学 | Obstacle detection method and system considering vehicle bump |
CN111381248A (en) * | 2020-03-23 | 2020-07-07 | 湖南大学 | Obstacle detection method and system considering vehicle bump |
CN111429528A (en) * | 2020-04-07 | 2020-07-17 | 高深智图(广州)科技有限公司 | Large-scale distributed high-precision map data processing system |
CN111765886A (en) * | 2020-05-18 | 2020-10-13 | 浙江西贝虎特种车辆股份有限公司 | Multi-terminal collaborative forest crown lower landform mapping system and method |
WO2021232227A1 (en) * | 2020-05-19 | 2021-11-25 | 深圳市大疆创新科技有限公司 | Point cloud frame construction method, target detection method, ranging apparatus, movable platform, and storage medium |
CN111710039A (en) * | 2020-06-03 | 2020-09-25 | 纵目科技(上海)股份有限公司 | Method, system, terminal and storage medium for constructing high-precision map |
CN111710040A (en) * | 2020-06-03 | 2020-09-25 | 纵目科技(上海)股份有限公司 | Method, system, terminal and storage medium for constructing high-precision map |
CN111710040B (en) * | 2020-06-03 | 2024-04-09 | 纵目科技(上海)股份有限公司 | High-precision map construction method, system, terminal and storage medium |
CN113819914A (en) * | 2020-06-19 | 2021-12-21 | 北京图森未来科技有限公司 | Map construction method and device |
CN113759369A (en) * | 2020-06-28 | 2021-12-07 | 北京京东乾石科技有限公司 | Image establishing method and device based on double multiline radar |
CN113759369B (en) * | 2020-06-28 | 2023-12-05 | 北京京东乾石科技有限公司 | Graph construction method and device based on double multi-line radar |
CN112086010B (en) * | 2020-09-03 | 2022-03-18 | 中国第一汽车股份有限公司 | Map generation method, map generation device, map generation equipment and storage medium |
CN112086010A (en) * | 2020-09-03 | 2020-12-15 | 中国第一汽车股份有限公司 | Map generation method, map generation device, map generation equipment and storage medium |
CN112067007B (en) * | 2020-11-12 | 2021-01-29 | 湖北亿咖通科技有限公司 | Map generation method, computer storage medium, and electronic device |
CN112067007A (en) * | 2020-11-12 | 2020-12-11 | 湖北亿咖通科技有限公司 | Map generation method, computer storage medium, and electronic device |
CN112767458B (en) * | 2020-11-13 | 2022-07-29 | 武汉中海庭数据技术有限公司 | Method and system for registering laser point cloud and image |
CN112767458A (en) * | 2020-11-13 | 2021-05-07 | 武汉中海庭数据技术有限公司 | Method and system for registering laser point cloud and image |
CN112799096A (en) * | 2021-04-08 | 2021-05-14 | 西南交通大学 | Map construction method based on low-cost vehicle-mounted two-dimensional laser radar |
CN113034566B (en) * | 2021-05-28 | 2021-09-24 | 湖北亿咖通科技有限公司 | High-precision map construction method and device, electronic equipment and storage medium |
CN113034566A (en) * | 2021-05-28 | 2021-06-25 | 湖北亿咖通科技有限公司 | High-precision map construction method and device, electronic equipment and storage medium |
CN113706676B (en) * | 2021-08-26 | 2024-01-16 | 京东鲲鹏(江苏)科技有限公司 | Model self-supervision training method and device for point cloud data |
CN113706676A (en) * | 2021-08-26 | 2021-11-26 | 京东鲲鹏(江苏)科技有限公司 | Model self-supervision training method and device for point cloud data |
CN114332232A (en) * | 2022-03-11 | 2022-04-12 | 中国人民解放军国防科技大学 | Smart phone indoor positioning method based on space point, line and surface feature hybrid modeling |
CN115267725B (en) * | 2022-09-27 | 2023-01-31 | 上海仙工智能科技有限公司 | Drawing establishing method and device based on single-line laser radar and storage medium |
CN115267725A (en) * | 2022-09-27 | 2022-11-01 | 上海仙工智能科技有限公司 | Drawing establishing method and device based on single-line laser radar and storage medium |
CN115638787A (en) * | 2022-12-23 | 2023-01-24 | 安徽蔚来智驾科技有限公司 | Digital map generation method, computer readable storage medium and electronic device |
Also Published As
Publication number | Publication date |
---|---|
CN109934920B (en) | 2019-08-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109934920B (en) | High-precision three-dimensional point cloud map constructing method based on low-cost equipment | |
CN111522043B (en) | Unmanned vehicle laser radar quick re-matching positioning method | |
CN109341706B (en) | Method for manufacturing multi-feature fusion map for unmanned vehicle | |
US11802769B2 (en) | Lane line positioning method and apparatus, and storage medium thereof | |
CN101241011B (en) | High precision positioning and posture-fixing device on laser radar platform and method | |
CN103411609B (en) | A kind of aircraft return route planing method based on online composition | |
CN111426320B (en) | Vehicle autonomous navigation method based on image matching/inertial navigation/milemeter | |
CN105930819A (en) | System for real-time identifying urban traffic lights based on single eye vision and GPS integrated navigation system | |
CN104180793A (en) | Device and method for obtaining mobile spatial information for digital city construction | |
CN110187375A (en) | A kind of method and device improving positioning accuracy based on SLAM positioning result | |
CN106226780A (en) | Many rotor-wing indoors alignment system based on scanning laser radar and implementation method | |
CN104655135B (en) | A kind of aircraft visual navigation method based on terrestrial reference identification | |
CN109710724A (en) | A kind of method and apparatus of building point cloud map | |
CN109507706B (en) | GPS signal loss prediction positioning method | |
CN102506867A (en) | SINS (strap-down inertia navigation system)/SMANS (scene matching auxiliary navigation system) combined navigation method based on Harris comer matching and combined navigation system | |
CN114485654A (en) | Multi-sensor fusion positioning method and device based on high-precision map | |
US20230236280A1 (en) | Method and system for positioning indoor autonomous mobile robot | |
CN111273312A (en) | Intelligent vehicle positioning and loop-back detection method | |
CN113419235A (en) | Unmanned aerial vehicle positioning method based on millimeter wave radar | |
CN114019552A (en) | Bayesian multi-sensor error constraint-based location reliability optimization method | |
CN112365542A (en) | Pose calibration method, pose calibration equipment and automatic control system | |
CN111123914A (en) | Vision scene-based direction estimation method for mowing robot | |
CN112098926B (en) | Intelligent angle measurement training sample generation method by using unmanned plane platform | |
CN107705272A (en) | A kind of high-precision geometric correction method of aerial image | |
Guo et al. | Novel Trajectory Optimization Algorithm of Vehicle-borne LiDAR Mobile Measurement System. |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CP02 | Change in the address of a patent holder | ||
CP02 | Change in the address of a patent holder |
Address after: 210012 room 401-404, building 5, chuqiaocheng, No. 57, Andemen street, Yuhuatai District, Nanjing, Jiangsu Province Patentee after: AUTOCORE INTELLIGENT TECHNOLOGY (NANJING) Co.,Ltd. Address before: 211800 building 12-289, 29 buyue Road, Qiaolin street, Pukou District, Nanjing City, Jiangsu Province Patentee before: AUTOCORE INTELLIGENT TECHNOLOGY (NANJING) Co.,Ltd. |