CN106980657A - A kind of track level electronic map construction method based on information fusion - Google Patents
A kind of track level electronic map construction method based on information fusion Download PDFInfo
- Publication number
- CN106980657A CN106980657A CN201710152964.1A CN201710152964A CN106980657A CN 106980657 A CN106980657 A CN 106980657A CN 201710152964 A CN201710152964 A CN 201710152964A CN 106980657 A CN106980657 A CN 106980657A
- Authority
- CN
- China
- Prior art keywords
- lane
- image
- electronic map
- panoramic
- frame image
- 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 OR CALCULATING; 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 OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4038—Image mosaicing, e.g. composing plane images from plane sub-images
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20048—Transform domain processing
- G06T2207/20061—Hough transform
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30248—Vehicle exterior or interior
- G06T2207/30252—Vehicle exterior; Vicinity of vehicle
- G06T2207/30256—Lane; Road marking
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Remote Sensing (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Processing Or Creating Images (AREA)
- Instructional Devices (AREA)
- Image Processing (AREA)
Abstract
本发明提供一种基于信息融合的车道级电子地图构建方法，具体过程为：步骤一，移动数据采集平台实时采集全景图像、定位数据及交通信号位置，基于逆投影变换将所述全景图像转换成全景俯视图，将所述定位数据、交通信号位置与全景俯视图进行融合；其中所述定位数据采用差分定位方式获得；步骤二，将融合后的全景俯视图进行拼接，生成车道级电子地图。本发明在进行电子地图构建时，将采集的全景图像转换成全景俯视图，同时融合了利用差分定位方式获得准确的定位数据，因此生成电子地图可以具体精确到车道。
The present invention provides a lane-level electronic map construction method based on information fusion. The specific process is as follows: step 1, the mobile data acquisition platform collects panoramic images, positioning data and traffic signal positions in real time, and converts the panoramic images into Panoramic bird's-eye view, merging the positioning data, traffic signal position and panoramic bird's-eye view; wherein the positioning data is obtained by differential positioning; Step 2, splicing the fused panoramic bird's-eye view to generate a lane-level electronic map. When constructing the electronic map, the present invention converts the collected panoramic image into a panoramic top view, and at the same time integrates the accurate positioning data obtained by using the differential positioning method, so that the generated electronic map can be specific and accurate to the lane.
Description
Technical Field
The invention belongs to the technical field of intelligent vehicles and geographic information systems, and particularly relates to a lane-level electronic map construction method based on information fusion.
Background
An Intelligent Vehicle (IV) is a mobile robot capable of continuously and automatically running in real time under road and field environments, is also an important component of the research of an Intelligent traffic system and a ground unmanned combat system, relates to a plurality of scientific and technical fields such as control science, computer science, information processing, sensor technology, artificial intelligence and the like, is a comprehensive Intelligent system integrating key technologies and functions such as environment perception, planning decision, behavior control and execution and the like, has research results widely applied to various fields such as military, civil and scientific research and has important research and application values.
The high-precision electronic map is an important component of the intelligent vehicle applied to the structured traffic environment, and the electronic map can effectively reduce the dependence of the intelligent vehicle on a high-precision sensing system. After the high-precision traffic environment map is obtained, the intelligent vehicle does not need to extract a feasible region from the environment information obtained by the sensing system, the intelligent vehicle can move forward while exploring, the intelligent vehicle is matched with the road network of the electronic map, a road section reaching a destination is continuously obtained from the road provided by the electronic map, and other traffic participants in the road section are sensed and avoided in real time during driving until the task is completed.
However, in recent years, with the wide application of intelligent vehicles in intelligent transportation systems, driving assistance and intelligent transportation, higher requirements are put on vehicle-mounted electronic maps, the electronic maps are required to reach lane-level accuracy, the existing electronic maps cannot meet the requirements of the applications, and an effective method for constructing the lane-level electronic maps is urgently needed.
Disclosure of Invention
In view of the above, the invention provides a lane-level electronic map construction method based on information fusion, and a map constructed by using the method can be accurately positioned to each lane, so that reliable guarantee is provided for the driving of vehicles.
The technical scheme for realizing the invention is as follows:
a lane-level electronic map construction method based on information fusion comprises the following specific processes:
firstly, a mobile data acquisition platform acquires a panoramic image, positioning data and a traffic signal position in real time, converts the panoramic image into a panoramic top view based on inverse projection transformation, and fuses the positioning data, the traffic signal position and the panoramic top view; the positioning data is obtained by adopting a differential positioning mode;
and step two, splicing the fused panoramic top views to generate a lane-level electronic map.
Furthermore, the method for acquiring the positioning data of the present invention is as follows: and erecting a differential base station on a platform with a known position, wherein the base station transmits real-time differential information to the mobile data acquisition platform by using a communication module, and the mobile data acquisition platform calculates the accurate positioning data of the mobile data acquisition platform according to the position of the base station and the differential information.
Further, the traffic signal position of the invention is obtained by adopting the following mode: firstly, a mobile data acquisition platform acquires an image of a traffic signal; secondly, marking an area where traffic signals possibly exist in the image by an image sequence detector; and finally, the tracker rejects the false detection area in the marking area to obtain the traffic signal position.
Further, the specific process of image stitching in the second step of the present invention is as follows:
step 201, dividing an image acquisition area passed by a mobile data acquisition platform into a plurality of grids with the same size;
step 202, judging whether the current frame image and the previous frame image correspond to the same grid;
step 203, if yes, splicing the current frame image and the previous frame image together according to the position relationship, otherwise, storing the splicing result of the previous frame image, and judging whether the grid corresponding to the current frame image has a stored image;
if so, splicing the stored image with the current frame image together according to the position relationship, otherwise, establishing a storage area of the grid corresponding to the current frame image, and storing the current frame image in the area;
step 204, processing all the fused panoramic overhead images according to the method of step 202-203 to obtain a spliced image corresponding to each grid;
and step 205, splicing the spliced images corresponding to the multiple grids together to generate the lane-level electronic map.
Further, in step 202 of the present invention, the determination is: and identifying the images by utilizing the position information of the mobile data acquisition and acquisition platform when each image is acquired, and judging according to the identification.
A lane-level electronic map construction method based on information fusion comprises the following specific processes:
firstly, a mobile data acquisition platform acquires a panoramic image, positioning data, a traffic signal position and road boundary information in real time, converts the panoramic image into a panoramic top view based on inverse projection transformation, and fuses the positioning data, the traffic signal position, the road boundary information and the panoramic top view; the positioning data is obtained by adopting a differential positioning mode;
splicing the fused panoramic top views to obtain a base map of the lane-level electronic map;
step three, generating a topological relation of the electronic map according to traffic rules and steering information among lanes, and merging the topological relation with the base map obtained in the step two;
and step four, setting a corresponding attribute table for each lane on the image, and generating a lane-level electronic map suitable for the unmanned ground vehicle.
Further, the road boundary information of the present invention is obtained by the following method: the mobile data acquisition platform acquires surrounding environment point cloud data, and road boundary information is determined through multi-feature Hough transformation.
Furthermore, the attribute table comprises a line data set 'road' attribute, a point data set 'road node' attribute and a point data set 'traffic sign' attribute; wherein,
the line data set road attribute comprises the distance between a lane and a left boundary of the road, the distance between the lane and a right boundary of the road, speed limit information of the lane, steering information of the lane, a merging attribute of the lane and the driving direction of the lane;
the point data set 'road node' attribute comprises whether the road node is an intersection or not and whether the road node is an intersection containing a traffic light or not;
the point data set "traffic sign" attributes include the type and attribute values of the traffic sign.
Advantageous effects
(1) When the electronic map is constructed, the acquired panoramic image is converted into the panoramic top view, and the accurate positioning data obtained by using a differential positioning mode is fused, so that the generated electronic map can be specifically accurate to a lane.
(2) When the high-precision electronic map is generated, the invention provides the method for processing the massive image data by using the grid mode, thereby effectively avoiding the condition that the image data cannot be processed due to overlarge data volume.
(3) The invention creates the attribute table for different geographic objects and provides reliable guarantee for the safe driving of the intelligent vehicle in the structured environment.
Drawings
FIG. 1 is a flow chart of a lane-level electronic map construction method based on information fusion;
FIG. 2 is a schematic diagram of a framework of a mobile data acquisition platform;
FIG. 3 is a design image grid coordinate system;
FIG. 4 is a flow chart of generating a base map of a high-precision electronic map;
FIG. 5 is a panoramic image after acquisition and processing;
FIG. 6 is a bottom view of a high-precision electronic map;
fig. 7 is a generated lane-level electronic map.
Detailed Description
The invention is described in detail below, by way of example, with reference to the accompanying drawings.
The invention provides a lane-level electronic map construction method based on information fusion, which comprises the following specific processes as shown in figure 1:
firstly, a mobile data acquisition platform acquires a panoramic image, positioning data and a traffic signal position in real time, converts the panoramic image into a panoramic top view based on inverse projection transformation, and fuses the positioning data, the traffic signal position and the panoramic top view; the positioning data is obtained by adopting a differential positioning mode;
and step two, splicing the fused panoramic top views to generate a lane-level electronic map.
According to the invention, the acquired panoramic image is converted into the panoramic top view which is used as the base map of the electronic map, so that each lane can be clearly seen by the constructed electronic map; meanwhile, the positioning data fused with the panoramic top view is obtained by adopting a differential positioning mode, and compared with the existing GPS positioning mode of the electronic map, the positioning generated by the invention has high precision.
The preferred way of the mobile data acquisition platform to acquire data in real time in this embodiment is as follows:
collecting panoramic images: panoramic image information is required to be collected to be used as a map base map for constructing a high-precision electronic map. Before acquiring a panoramic image, firstly, a panoramic camera on a mobile data acquisition platform needs to be calibrated through a calibration plate, and then a panoramic top view is obtained based on an inverse projection transformation (IPM) algorithm. In addition, in order to splice different panoramic images during post-processing, the position of the data acquisition platform when the images are acquired needs to be utilized to identify the images, and the position information of the data acquisition platform is marked at the lower right corner of the images in a two-dimensional code mode.
Collecting positioning data: the construction of lane-level electronic maps requires that the positioning data can distinguish different lanes, so the accuracy of the positioning data is at least a decimeter level. Currently, the single-point positioning accuracy of the most widely applied satellite positioning navigation system (such as a GPS) is generally more than a meter level. Therefore, the differential positioning technology is adopted in the embodiment, the differential base station is erected on a platform with a known position, and the base station transmits real-time differential information to the mobile data acquisition platform through the mobile communication module, so that the positioning precision can reach centimeter level.
Collecting the position of a traffic signal: the traffic signal comprises a traffic light and a traffic sign, after the image of the traffic light and the traffic sign is obtained through the monocular camera, firstly, the image sequence detector marks the area in the image where the traffic light and the traffic sign possibly exist, and the marked image is regarded as the noisy observation of target positioning; then, the tracker processes the noisy observation by using a data association method in a multi-target tracking algorithm, extracts a real candidate region from a target from the disordered observation and eliminates a false detection region to obtain the positions of the traffic lights and the traffic signs.
The mobile data acquisition platform also acquires surrounding environment point cloud data through a laser radar, determines road boundary information through multi-feature Hough transformation, and fuses the road boundary information and the panoramic top view.
Fig. 2 shows a schematic diagram of devices for collecting data on the mobile data collection platform.
As shown in fig. 3, the specific process of splicing the fused panoramic top view is as follows:
step 201, dividing the image acquisition area passed by the mobile data acquisition platform into a plurality of grids with the same size, each grid corresponding to a determined range, in this example, one grid with the size of 1620m × 360m (27000 pixels × 6000 pixels), and selecting origin coordinates (x) according to the coordinate range of the data acquisition area0,y0) And at the same time, determining the sequence number (i, j) of each grid, as shown in fig. 4;
step 202, determining the grid corresponding to the current frame image according to the position information identified on the image, and judging whether the serial number of the grid is the same as the serial number of the grid corresponding to the previous frame image, namely judging whether the current frame image and the previous frame image correspond to the same grid;
step 203, splicing the two images together according to the position relationship if the serial numbers are the same, namely corresponding to the same grid, otherwise, storing the splicing result of the previous frame of image, and judging whether the grid corresponding to the current frame of image has a stored image before;
if the stored image exists, the stored image and the current frame image are spliced together according to the position relation, otherwise, a region is newly built in the memory to serve as a storage region of a grid corresponding to the current frame image, and the current frame image is stored in the region;
step 204, processing all the fused panoramic overhead images according to the method of step 202-203 to obtain a plurality of images representing different grids;
and step 205, splicing the images representing different grids together according to the serial numbers of the grids to obtain a base map of the high-precision electronic map.
The invention relates to a lane-level electronic map construction method based on information fusion, which comprises the following specific processes:
firstly, a mobile data acquisition platform acquires a panoramic image, positioning data, a traffic signal position and road boundary information in real time, converts the panoramic image into a panoramic top view based on inverse projection transformation, and fuses the positioning data, the traffic signal position, the road boundary information and the panoramic top view; the positioning data is obtained by adopting a differential positioning mode;
splicing the fused panoramic top views;
step three, generating a topological relation of the electronic map according to traffic rules and steering information among lanes, and fusing the topological relation with the image obtained by splicing in the step two; the topological relation is an important component of the electronic map and is a necessary condition for applying the electronic map to path planning and shortest path analysis.
And step four, setting a corresponding attribute table for each lane on the image according to the characteristics of different geographic objects, and generating a lane-level electronic map suitable for the application of the unmanned ground vehicle.
The specific process of constructing the attribute table for different geographic objects is as follows:
first, a line data set "road" is shown in the attribute table 1.
TABLE 1 line data set "road" attribute
Wherein the Left _ Width and Right _ Width attributes represent distances of the current lane from the Left and Right boundaries. The two attributes give left and right boundaries when the unmanned ground vehicle is locally planned, and play an important role in guiding safe driving of the unmanned ground vehicle, and the attributes are calculated by collected road boundary data. The Speed _ Limit attribute represents the Speed Limit information of the current lane, and driving in the Speed Limit range is one of important criteria of intelligent driving; meanwhile, for the driving safety of the vehicle, the electronic map constructed by the invention also limits the speed of the lanes near the intersection according to the steering information of the corresponding lanes (for example, the speed limit of a straight lane is 30km/h, the speed limit of a left-turn right-turn lane is 15km/h, and the speed limit of a U-turn lane is 10 km/h). The Change _ Direction attribute is steering information of the current lane, wherein 0 is straight, 1 is left turn, 2 is right turn, and 3 is turn around. The if _ CrossLine attribute is whether the current lane allows the merging, wherein 0 is prohibited merging, 1 is allowed merging, and vehicles in some areas of the road (such as the vicinity of an intersection) are not allowed to be merged, so that the addition of the attribute has an important indication effect on the unmanned ground vehicle to drive according to the traffic rules. The Direction attribute indicates the Direction of the current lane and is indicated by the Direction angle of the current lane.
The attribute tables corresponding to the point data sets "road node" and "traffic sign" are shown in table 2 and table 3, respectively.
TABLE 2 Attribute for Point data set "road node
The attributes corresponding to the "road node" mainly include an if _ Intersection and an if _ TrafficLight attribute, and respectively indicate whether the road node is an Intersection and whether the road node is an Intersection containing traffic lights.
Table 3 attributes of the point data set "road sign
The attributes corresponding to the traffic sign are Category and Value, the Category attribute represents the type of the traffic sign (such as speed limit, no-go, etc.), and the Value attribute represents the Value of the corresponding traffic sign (such as 40km/h, the attribute Value is 40).
The invention takes an intelligent vehicle research and development center in the mature city of Jiangsu province as a test field to construct an electronic map to verify the effectiveness of the invention.
(1) Firstly, data required by constructing an electronic map are acquired by using a mobile data acquisition platform. The acquired and processed panoramic image data is shown in fig. 5.
(2) Next, according to steps 201 to 205, a base map of the high-precision electronic map is generated, and the obtained base map is shown in fig. 6.
(3) Finally, a topological relation of the electronic map is generated according to the traffic rules and the steering information between the lanes, and the lane-level electronic map obtained according to the traffic rules reflecting the traffic rules of the urban roads is shown in fig. 7.
In summary, the above description is only a preferred example of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A lane-level electronic map construction method based on information fusion is characterized by comprising the following specific processes:
firstly, a mobile data acquisition platform acquires a panoramic image, positioning data and a traffic signal position in real time, converts the panoramic image into a panoramic top view based on inverse projection transformation, and fuses the positioning data, the traffic signal position and the panoramic top view; the positioning data is obtained by adopting a differential positioning mode;
and step two, splicing the fused panoramic top views to generate a lane-level electronic map.
2. The method for constructing the lane-level electronic map based on the information fusion as claimed in claim 1, wherein the positioning data is obtained by: and erecting a differential base station on a platform with a known position, wherein the base station transmits real-time differential information to the mobile data acquisition platform by using a communication module, and the mobile data acquisition platform calculates the accurate positioning data of the mobile data acquisition platform according to the position of the base station and the differential information.
3. The lane-level electronic map construction method based on information fusion of claim 1, wherein the traffic signal position is obtained by: firstly, a mobile data acquisition platform acquires an image of a traffic signal; secondly, marking an area where traffic signals possibly exist in the image by an image sequence detector; and finally, the tracker rejects the false detection area in the marking area to obtain the traffic signal position.
4. The lane-level electronic map construction method based on information fusion as claimed in claim 1, wherein the specific process of image stitching in step two is as follows:
step 201, dividing an image acquisition area passed by a mobile data acquisition platform into a plurality of grids with the same size;
step 202, judging whether the current frame image and the previous frame image correspond to the same grid;
step 203, if yes, splicing the current frame image and the previous frame image together according to the position relationship, otherwise, storing the splicing result of the previous frame image, and judging whether the grid corresponding to the current frame image has a stored image;
if so, splicing the stored image with the current frame image together according to the position relationship, otherwise, establishing a storage area of the grid corresponding to the current frame image, and storing the current frame image in the area;
step 204, processing all the fused panoramic overhead images according to the method of step 202-203 to obtain a spliced image corresponding to each grid;
and step 205, splicing the spliced images corresponding to the multiple grids together to generate the lane-level electronic map.
5. The method for constructing the lane-level electronic map based on information fusion according to claim 4, wherein the judgment in step 202 is: and identifying the images by utilizing the position information of the mobile data acquisition and acquisition platform when each image is acquired, and judging according to the identification.
6. A lane-level electronic map construction method based on information fusion is characterized by comprising the following specific processes:
firstly, a mobile data acquisition platform acquires a panoramic image, positioning data, a traffic signal position and road boundary information in real time, converts the panoramic image into a panoramic top view based on inverse projection transformation, and fuses the positioning data, the traffic signal position, the road boundary information and the panoramic top view; the positioning data is obtained by adopting a differential positioning mode;
splicing the fused panoramic top views to obtain a base map of the lane-level electronic map;
step three, generating a topological relation of the electronic map according to traffic rules and steering information among lanes, and merging the topological relation with the base map obtained in the step two;
and step four, setting a corresponding attribute table for each lane on the image, and generating a lane-level electronic map suitable for the unmanned ground vehicle.
7. The information fusion-based lane-level electronic map construction method according to claim 6, wherein the road boundary information is obtained by: the mobile data acquisition platform acquires surrounding environment point cloud data, and road boundary information is determined through multi-feature Hough transformation.
8. The information fusion-based lane-level electronic map construction method according to claim 6, wherein the attribute table comprises a line data set road attribute, a point data set road node attribute and a point data set traffic sign attribute; wherein,
the line data set road attribute comprises the distance between a lane and a left boundary of the road, the distance between the lane and a right boundary of the road, speed limit information of the lane, steering information of the lane, a merging attribute of the lane and the driving direction of the lane;
the point data set 'road node' attribute comprises whether the road node is an intersection or not and whether the road node is an intersection containing a traffic light or not;
the point data set "traffic sign" attributes include the type and attribute values of the traffic sign.
9. The lane-level electronic map construction method based on information fusion as claimed in claim 6, wherein the specific process of image stitching in step two is as follows:
step 201, dividing an image acquisition area passed by a mobile data acquisition platform into a plurality of grids with the same size;
step 202, judging whether the current frame image and the previous frame image correspond to the same grid;
step 203, if yes, splicing the current frame image and the previous frame image together according to the position relationship, otherwise, storing the splicing result of the previous frame image, and judging whether the grid corresponding to the current frame image has a stored image;
if so, splicing the stored image with the current frame image together according to the position relationship, otherwise, establishing a storage area of the grid corresponding to the current frame image, and storing the current frame image in the area;
step 204, processing all the fused panoramic overhead images according to the method of step 202-203 to obtain a spliced image corresponding to each grid;
and step 205, splicing the spliced images corresponding to the multiple grids together to obtain a base map of the lane-level electronic map.
10. The method for constructing the lane-level electronic map based on information fusion according to claim 9, wherein the determination in step 202 is: and identifying the images by utilizing the position information of the mobile data acquisition and acquisition platform when each image is acquired, and judging according to the identification.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710152964.1A CN106980657A (en) | 2017-03-15 | 2017-03-15 | A kind of track level electronic map construction method based on information fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710152964.1A CN106980657A (en) | 2017-03-15 | 2017-03-15 | A kind of track level electronic map construction method based on information fusion |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106980657A true CN106980657A (en) | 2017-07-25 |
Family
ID=59338977
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710152964.1A Pending CN106980657A (en) | 2017-03-15 | 2017-03-15 | A kind of track level electronic map construction method based on information fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106980657A (en) |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107976182A (en) * | 2017-11-30 | 2018-05-01 | 深圳市隐湖科技有限公司 | A kind of Multi-sensor Fusion builds drawing system and its method |
| CN108388641A (en) * | 2018-02-27 | 2018-08-10 | 广东方纬科技有限公司 | A kind of means of transportation based on deep learning ground drawing generating method and system |
| CN108981726A (en) * | 2018-06-09 | 2018-12-11 | 安徽宇锋智能科技有限公司 | Unmanned vehicle semanteme Map building and building application method based on perceptual positioning monitoring |
| CN109141446A (en) * | 2018-07-04 | 2019-01-04 | 百度在线网络技术（北京）有限公司 | For obtaining the method, apparatus, equipment and computer readable storage medium of map |
| CN109186618A (en) * | 2018-08-31 | 2019-01-11 | 平安科技（深圳）有限公司 | Map constructing method, device, computer equipment and storage medium |
| CN109635701A (en) * | 2018-12-05 | 2019-04-16 | 宽凳（北京）科技有限公司 | Lane attribute acquisition methods, device and computer readable storage medium |
| CN109631873A (en) * | 2018-11-01 | 2019-04-16 | 百度在线网络技术（北京）有限公司 | Road generation method, device and the readable storage medium storing program for executing of high-precision map |
| CN109949325A (en) * | 2019-02-27 | 2019-06-28 | 上海晶赞融宣科技有限公司 | Map boundary line determines method, apparatus and computer storage medium |
| CN110162589A (en) * | 2019-05-31 | 2019-08-23 | 北京百度网讯科技有限公司 | Assignment method, device, electronic equipment, the computer-readable medium of road speed limit value |
| CN110415527A (en) * | 2019-07-30 | 2019-11-05 | 公安部交通管理科学研究所 | Electric bicycle monitoring method and system based on Beidou ground enhancement technology |
| WO2020029601A1 (en) * | 2018-08-06 | 2020-02-13 | 武汉中海庭数据技术有限公司 | Method and system for constructing transverse topological relationship of lanes in map, and memory |
| CN110969574A (en) * | 2018-09-29 | 2020-04-07 | 广州汽车集团股份有限公司 | Vehicle-mounted panoramic map creation method and device |
| CN111311945A (en) * | 2020-02-20 | 2020-06-19 | 南京航空航天大学 | A driving decision-making system and method integrating visual and sensor information |
| CN111582019A (en) * | 2020-03-24 | 2020-08-25 | 北京掌行通信息技术有限公司 | Method, system, terminal and storage medium for judging unmanned vehicle lane level scene |
| CN112082567A (en) * | 2020-09-05 | 2020-12-15 | 上海智驾汽车科技有限公司 | Map path planning method based on combination of improved Astar and Grey wolf algorithm |
| CN112797991A (en) * | 2021-02-09 | 2021-05-14 | 中科大路(青岛)科技有限公司 | Method and system for generating driving path of unmanned vehicle |
| CN112833891A (en) * | 2020-12-31 | 2021-05-25 | 武汉光庭信息技术股份有限公司 | Road data and lane-level map data fusion method based on satellite film recognition |
| KR20210078532A (en) * | 2018-10-24 | 2021-06-28 | 웨이모 엘엘씨 | Traffic light detection and lane condition recognition for autonomous vehicles |
| CN113051304A (en) * | 2021-04-02 | 2021-06-29 | 中国有色金属长沙勘察设计研究院有限公司 | Calculation method for fusion of radar monitoring data and three-dimensional point cloud |
| CN113837064A (en) * | 2021-09-22 | 2021-12-24 | 广州小鹏自动驾驶科技有限公司 | Road identification method, system and readable storage medium |
| CN117109623A (en) * | 2023-10-09 | 2023-11-24 | 深圳市微克科技有限公司 | An intelligent wearable navigation interaction method, system and medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103978978A (en) * | 2014-05-26 | 2014-08-13 | 武汉理工大学 | Inversion projection transformation based lane keeping method |
| CN105946853A (en) * | 2016-04-28 | 2016-09-21 | 中山大学 | Long-distance automatic parking system and method based on multi-sensor fusion |
-
2017
- 2017-03-15 CN CN201710152964.1A patent/CN106980657A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103978978A (en) * | 2014-05-26 | 2014-08-13 | 武汉理工大学 | Inversion projection transformation based lane keeping method |
| CN105946853A (en) * | 2016-04-28 | 2016-09-21 | 中山大学 | Long-distance automatic parking system and method based on multi-sensor fusion |
Non-Patent Citations (5)
| Title |
|---|
| 史军勇: "《嵌入式GPS导航应用研究》", 31 May 2015 * |
| 周春平: "《地理空间情报教程》", 31 July 2016, 国防大学出版社 * |
| 宁津生等: "《测绘学概论》", 30 September 2016 * |
| 易思蓉: "《铁路数字化选线设计系统的理论与方法》", 30 November 2011, 西南交通大学出版社 * |
| 贺勇等: "《基于多传感器的车道级高精细地图制作方法》", 《长安大学学报（自然科学版）》 * |
Cited By (34)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107976182A (en) * | 2017-11-30 | 2018-05-01 | 深圳市隐湖科技有限公司 | A kind of Multi-sensor Fusion builds drawing system and its method |
| CN108388641A (en) * | 2018-02-27 | 2018-08-10 | 广东方纬科技有限公司 | A kind of means of transportation based on deep learning ground drawing generating method and system |
| CN108388641B (en) * | 2018-02-27 | 2022-02-01 | 广东方纬科技有限公司 | Traffic facility map generation method and system based on deep learning |
| CN108981726A (en) * | 2018-06-09 | 2018-12-11 | 安徽宇锋智能科技有限公司 | Unmanned vehicle semanteme Map building and building application method based on perceptual positioning monitoring |
| CN109141446A (en) * | 2018-07-04 | 2019-01-04 | 百度在线网络技术（北京）有限公司 | For obtaining the method, apparatus, equipment and computer readable storage medium of map |
| CN109141446B (en) * | 2018-07-04 | 2021-11-12 | 阿波罗智能技术(北京)有限公司 | Method, apparatus, device and computer-readable storage medium for obtaining map |
| US11243086B2 (en) | 2018-07-04 | 2022-02-08 | Apollo Intelligent Driving Technology (Beijing) Co., Ltd. | Method, device and apparatus for acquiring map, and computer readable storage medium |
| WO2020029601A1 (en) * | 2018-08-06 | 2020-02-13 | 武汉中海庭数据技术有限公司 | Method and system for constructing transverse topological relationship of lanes in map, and memory |
| US11182624B2 (en) | 2018-08-06 | 2021-11-23 | Wuhhan Kotel Big Date Corporation | Method, system and memory for constructing transverse topological relationship of lanes in high-definition map |
| CN109186618A (en) * | 2018-08-31 | 2019-01-11 | 平安科技（深圳）有限公司 | Map constructing method, device, computer equipment and storage medium |
| CN110969574A (en) * | 2018-09-29 | 2020-04-07 | 广州汽车集团股份有限公司 | Vehicle-mounted panoramic map creation method and device |
| KR102558774B1 (en) * | 2018-10-24 | 2023-07-25 | 웨이모 엘엘씨 | Traffic Light Detection and Lane Condition Recognition for Autonomous Vehicles |
| US11645852B2 (en) | 2018-10-24 | 2023-05-09 | Waymo Llc | Traffic light detection and lane state recognition for autonomous vehicles |
| KR20210078532A (en) * | 2018-10-24 | 2021-06-28 | 웨이모 엘엘씨 | Traffic light detection and lane condition recognition for autonomous vehicles |
| CN113168513A (en) * | 2018-10-24 | 2021-07-23 | 伟摩有限责任公司 | Traffic light detection and lane status identification for autonomous vehicles |
| CN109631873A (en) * | 2018-11-01 | 2019-04-16 | 百度在线网络技术（北京）有限公司 | Road generation method, device and the readable storage medium storing program for executing of high-precision map |
| CN109635701B (en) * | 2018-12-05 | 2023-04-18 | 宽凳（北京）科技有限公司 | Lane passing attribute acquisition method, lane passing attribute acquisition device and computer readable storage medium |
| CN109635701A (en) * | 2018-12-05 | 2019-04-16 | 宽凳（北京）科技有限公司 | Lane attribute acquisition methods, device and computer readable storage medium |
| CN109949325A (en) * | 2019-02-27 | 2019-06-28 | 上海晶赞融宣科技有限公司 | Map boundary line determines method, apparatus and computer storage medium |
| CN110162589A (en) * | 2019-05-31 | 2019-08-23 | 北京百度网讯科技有限公司 | Assignment method, device, electronic equipment, the computer-readable medium of road speed limit value |
| CN110415527A (en) * | 2019-07-30 | 2019-11-05 | 公安部交通管理科学研究所 | Electric bicycle monitoring method and system based on Beidou ground enhancement technology |
| CN111311945A (en) * | 2020-02-20 | 2020-06-19 | 南京航空航天大学 | A driving decision-making system and method integrating visual and sensor information |
| CN111582019A (en) * | 2020-03-24 | 2020-08-25 | 北京掌行通信息技术有限公司 | Method, system, terminal and storage medium for judging unmanned vehicle lane level scene |
| CN111582019B (en) * | 2020-03-24 | 2023-10-03 | 北京掌行通信息技术有限公司 | Determination methods, systems, terminals and storage media for lane-level scenarios for autonomous vehicles |
| CN112082567A (en) * | 2020-09-05 | 2020-12-15 | 上海智驾汽车科技有限公司 | Map path planning method based on combination of improved Astar and Grey wolf algorithm |
| CN112082567B (en) * | 2020-09-05 | 2023-06-02 | 上海智驾汽车科技有限公司 | Map path planning method based on combination of improved Astar and gray wolf algorithm |
| CN112833891A (en) * | 2020-12-31 | 2021-05-25 | 武汉光庭信息技术股份有限公司 | Road data and lane-level map data fusion method based on satellite film recognition |
| CN112797991A (en) * | 2021-02-09 | 2021-05-14 | 中科大路(青岛)科技有限公司 | Method and system for generating driving path of unmanned vehicle |
| CN113051304B (en) * | 2021-04-02 | 2022-06-24 | 中国有色金属长沙勘察设计研究院有限公司 | Calculation method for fusion of radar monitoring data and three-dimensional point cloud |
| CN113051304A (en) * | 2021-04-02 | 2021-06-29 | 中国有色金属长沙勘察设计研究院有限公司 | Calculation method for fusion of radar monitoring data and three-dimensional point cloud |
| CN113837064A (en) * | 2021-09-22 | 2021-12-24 | 广州小鹏自动驾驶科技有限公司 | Road identification method, system and readable storage medium |
| CN113837064B (en) * | 2021-09-22 | 2023-11-03 | 广州小鹏自动驾驶科技有限公司 | Road recognition method, system and readable storage medium |
| CN117109623A (en) * | 2023-10-09 | 2023-11-24 | 深圳市微克科技有限公司 | An intelligent wearable navigation interaction method, system and medium |
| CN117109623B (en) * | 2023-10-09 | 2024-09-13 | 深圳市微克科技股份有限公司 | Intelligent wearable navigation interaction method, system and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106980657A (en) | A kind of track level electronic map construction method based on information fusion | |
| US20240034309A1 (en) | Navigation in vehicle crossing scenarios | |
| CN110057373B (en) | Method, apparatus and computer storage medium for generating high-definition semantic map | |
| JP7432285B2 (en) | Lane mapping and navigation | |
| CN108303103B (en) | Method and device for determining target lane | |
| Brenner | Extraction of features from mobile laser scanning data for future driver assistance systems | |
| US20210311490A1 (en) | Crowdsourcing a sparse map for autonomous vehicle navigation | |
| EP3290952B1 (en) | Automatic localization geometry detection | |
| US10248124B2 (en) | Localizing vehicle navigation using lane measurements | |
| CN106441319B (en) | A system and method for generating a lane-level navigation map of an unmanned vehicle | |
| JP2022166185A (en) | Crowdsourcing and distribution of sparse maps and lane measurements for autonomous vehicle navigation | |
| US20200257301A1 (en) | Navigation by augmented path prediction | |
| CN102208035B (en) | Image processing system and position measuring system | |
| JP5505723B2 (en) | Image processing system and positioning system | |
| JP2022535351A (en) | System and method for vehicle navigation | |
| JP2023508769A (en) | Systems and methods for optimizing map tile requests for navigation | |
| CN108445503A (en) | The unmanned path planning algorithm merged with high-precision map based on laser radar | |
| JP2023532482A (en) | System and method for detecting open doors | |
| CN116997771A (en) | Vehicle and positioning method, device, equipment, computer-readable storage medium | |
| CN112880692A (en) | Map data annotation method and device and storage medium | |
| CN115205803A (en) | Automatic driving environment perception method, medium and vehicle | |
| CN118365812A (en) | Map construction method and device | |
| Křehlík et al. | Minimum required accuracy for HD maps | |
| CN115164924A (en) | Fusion positioning method, system, equipment and storage medium based on visual AI | |
| CN113390422B (en) | Automobile positioning method and device and computer storage 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: 20170725 |
|
| RJ01 | Rejection of invention patent application after publication |