CN113886634A - Lane line offline data visualization method and device - Google Patents
Lane line offline data visualization method and device Download PDFInfo
- Publication number
- CN113886634A CN113886634A CN202111158760.1A CN202111158760A CN113886634A CN 113886634 A CN113886634 A CN 113886634A CN 202111158760 A CN202111158760 A CN 202111158760A CN 113886634 A CN113886634 A CN 113886634A
- Authority
- CN
- China
- Prior art keywords
- target
- sensor
- lane line
- data
- time period
- 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
- 238000000034 method Methods 0.000 title claims abstract description 16
- 238000013079 data visualisation Methods 0.000 title claims description 5
- 238000007405 data analysis Methods 0.000 claims description 13
- 238000004458 analytical method Methods 0.000 claims description 12
- 238000012800 visualization Methods 0.000 claims description 11
- 238000012545 processing Methods 0.000 description 8
- 238000001514 detection method Methods 0.000 description 4
- 238000012896 Statistical algorithm Methods 0.000 description 3
- 238000007619 statistical method Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000007794 visualization technique Methods 0.000 description 3
- 206010039203 Road traffic accident Diseases 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 239000010931 gold Substances 0.000 description 1
- 229910052737 gold Inorganic materials 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000012106 screening analysis Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/74—Browsing; Visualisation therefor
- G06F16/743—Browsing; Visualisation therefor a collection of video files or sequences
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/71—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/7867—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, title and artist information, manually generated time, location and usage information, user ratings
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
- G06F9/45558—Hypervisor-specific management and integration aspects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
- G06F9/45558—Hypervisor-specific management and integration aspects
- G06F2009/4557—Distribution of virtual machine instances; Migration and load balancing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Human Computer Interaction (AREA)
- Library & Information Science (AREA)
- Traffic Control Systems (AREA)
Abstract
The scheme relates to a method and a device for visualizing lane line offline data, wherein the method comprises the following steps: acquiring and analyzing lane line offline data packets of each lane line sensor, and respectively storing the lane line offline data of each sensor into a first data container; time synchronization is carried out on lane line off-line data of each sensor stored in each first data container, and then the lane line off-line data are stored in a second data container; selecting a target time period and a lane line coefficient to be targeted, and extracting the off-line data of the target lane line of all the sensors in the target time period from the second data container; forming a first graph of the curve coefficient of each target lane line of each sensor changing along with time in a target time period; and calculating the mean value, the variance and/or the expected curve graph of the target lane curve coefficient of each sensor changing along with the time in the target time period based on the first curve graph of the target lane curve coefficient of each sensor changing along with the time in the target time period, and then performing output display.
Description
Technical Field
The invention belongs to the technical field of automatic driving control application, and particularly relates to a method for analyzing data of a sensing fusion lane line of an automatic driving vehicle.
Background
In recent years, laser radar cost is gradually lowered, high-precision maps basically cover national expressways, chip calculation power of cameras and radars is improved, and due to upgrading and large-scale popularization of sensor technologies, rapid improvement of automatic driving technologies is promoted, and automatic driving commercial mass production above the L3 level is made possible.
However, with the increase in the number of automatic driving sensors and the increase in sensor computing power, a large amount of data, particularly lidar and cameras, is generated, and it is estimated that 1TB of data is generated every 100KM road test. Data generated by the automatic driving road test comprise information of vehicles, laser radar point clouds, camera image data, map data and the like, and how to utilize the data gold mine for improving the performance and the system robustness of the automatic driving system becomes a new difficult problem.
The lane keeping function is the most basic and important part of the automatic driving function, the lane keeping function mainly ensures that a vehicle runs centrally on a structured road, and the lane keeping function directly affects the safety of the whole automatic driving system, namely, the transverse deviation control can cause traffic accidents and comfortableness, and the experience of passengers can be affected by the shaking in a lane.
The transverse control is directly influenced by combining the quality of the lane line output, if the output navigation angle (the relative position of the road lane line and the vehicle) of the lane line and the output curvature fluctuation of the lane line can cause transverse control jitter, and even serious traffic accidents are caused by collision to a lane guardrail and adjacent vehicles. How to improve the robustness of lane line output therefore directly affects the effectiveness of lateral (steering wheel) control and the stability of the autopilot system.
At present, a lane line mainly depends on a forward-looking camera, an image collected by a look-around camera is subjected to edge enhancement, binarization image processing, extraction of feature points of the inner edge of the lane line and finally hough change fitting to obtain the lane line, and the lane line is represented by a plurality of curve equations (wherein the curve variance correlation coefficient of the lane line) so that the visualization method provided by the patent can visually analyze and judge the problems of false detection and missed detection of the lane line.
However, the existing lane line offline data analysis method has the following obvious defects:
1. only a single signal line graph is displayed statically and globally (whole section of offline data), and the signal change of each time point cannot be displayed dynamically according to a time axis;
2. a numerical value statistic module is not added, so that a developer can not find potential rules of data conveniently.
The analysis based on the data must completely and correctly reflect the overall view of objective conditions, and under the guidance of the principle of practice, a large amount of abundant statistical data and data are processed, manufactured, analyzed and researched, so that the guidance direction can be provided for the subsequent development. The process of data processing is a complex process, and errors may be generated in the process from data collection to data screening and data analysis in this link, so that the wrong data needs to be screened in each link, and particularly, a process of cleaning the data can be well performed at the data processing stage.
In conclusion, the visual and dynamic display of the lane line data generated by the automatic driving is beneficial for developers to find potential problems in the automatic driving system from the road test data, the safety of the system is improved, and meanwhile, the numerical value statistical module can also provide sensor lane line multi-dimensional data for the developers, so that the optimization function development and the robustness of the system are improved.
Disclosure of Invention
The invention aims to provide an analysis method, a visualization method and a visualization device of lane line data based on automatic driving for developers, which are used for solving the problems of rapid and intuitive analysis and positioning of the developers from mass data, improving the efficiency and reducing the problem processing time.
The technical scheme adopted by the invention is as follows:
the invention provides a lane line offline data visualization method, which comprises the following steps:
acquiring and analyzing lane line offline data packets of each lane line sensor to obtain lane line offline data of each lane line sensor, and storing the lane line offline data of each sensor into a first data container respectively;
time synchronization is carried out on the lane line offline data of each sensor stored in each first data container, and then the lane line offline data of each sensor stored in each first data container after time synchronization is respectively added with the corresponding sensor zone bit and then is transferred into the same second data container;
selecting a target time period and a target lane line coefficient to be displayed, and extracting the target lane line offline data of all the sensors in the target time period from the second data container;
respectively establishing a Cartesian coordinate system with time as a horizontal axis and target lane curve coefficients as a vertical axis for each sensor to form a first curve graph of each target lane curve coefficient of each sensor along with time change in the target time period;
calculating a second plot of a mean of the target lane line curve coefficients of each sensor over time over the target time period, a third plot of a variance of the target lane line curve coefficients of each sensor over time over the target time period, and/or a fourth plot of the target lane line curve coefficients of each sensor expected to vary over time over the target time period, based on the first plot of the target lane line curve coefficients of each sensor over time over the target time period;
and carrying out output display on a second graph of the mean value of the target lane curve coefficients of each sensor changing along with time in the target time period, a third graph of the variance of the target lane curve coefficients of each sensor changing along with time in the target time period, and/or a fourth graph of the target lane curve coefficients of each sensor expected to change along with time in the target time period.
The invention also provides a lane line off-line data visualization device, which comprises:
the off-line data analysis module is used for acquiring and analyzing lane line off-line data packets of each lane line sensor to obtain lane line off-line data of each lane line sensor, and then storing the lane line off-line data of each sensor into a first data container;
the data unloading module is used for carrying out time synchronization on the lane line offline data of each sensor stored in each first data container, and unloading the lane line offline data of each sensor stored in each first data container after time synchronization into the same second data container after adding the corresponding sensor flag bit to the lane line offline data of each sensor stored in each first data container;
the time flow graph module is used for selecting a target time period and a target lane line coefficient to be displayed, and extracting the target lane line offline data of all the sensors in the target time period from the second data container; respectively establishing a Cartesian coordinate system with time as a horizontal axis and target lane curve coefficients as a vertical axis for each sensor to form a first curve graph of each target lane curve coefficient of each sensor along with time change in the target time period;
a numerical analysis module for calculating a second graph of a mean of the target lane line curve coefficients of each sensor over time within the target time period, a third graph of a variance of the target lane line curve coefficients of each sensor over time within the target time period, and/or a fourth graph of the target lane line curve coefficients of each sensor expected to change over time within the target time period, based on the first graph of the target lane line curve coefficients of each sensor over time within the target time period;
and the visualization module is used for outputting and displaying a second curve graph of the mean value of the target lane curve coefficients of each sensor, a third curve graph of the variance of the target lane curve coefficients of each sensor, and/or a fourth curve graph of the target lane curve coefficients of each sensor, which is expected to change along with time in the target time period, in the target time period.
The invention has the beneficial effects that:
1. by introducing the concept of time flow, the signal change can be dynamically displayed along with the change of time;
2. the problems of false detection and missed detection of the lane line can be visually analyzed and judged by the provided visualization method;
3. the method is convenient for developers to find potential rules of the sensor lane line data from multiple angles by adding data statistical analysis.
Drawings
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is a block diagram of the apparatus of the present invention.
Detailed Description
Referring to fig. 1 and 2, the invention provides an off-line data analysis visualization device for an automatic driving lane line, which comprises the following modules:
an offline data analysis module: the method is used for loading lane line offline data packets of lane line sensors (such as a forward-looking camera and a look-around camera) of the automatic driving vehicle, analyzing the lane line offline data of the sensors obtained after analysis and respectively storing the lane line offline data of the sensors into an independent data container.
In this embodiment, the lane line offline data analysis module specifically includes 3 components, which are respectively: the system comprises a data loading component, a data analysis component and a data storage component. The data loading component loads a lane line offline data packet to be processed at first; and then, a data analysis component is called to analyze the lane line offline data packets to obtain lane line offline data of each sensor, and the data analysis component is mainly used for receiving lane line offline data streams of one period according to different protocol rules (TPC/UDP/CAN) and analyzing original sensor signals. And finally, respectively storing the analyzed lane line offline data of each lane line sensor into a first data container by using a data storage component. For example, if there are n lane line sensors, the lane line offline data of the n analyzed lane line sensors are stored in the first data sensor a, respectively1To AnIn (1).
A data unloading module: and carrying out time synchronization on the automatic driving off-line data of the lane line sensors stored in the data containers, and then uniformly transferring the automatic driving off-line data to the same second data container. Meanwhile, an interface is reserved in the data unloading module, so that the automatic driving off-line data unloaded to the second data container can be conveniently cleaned.
The data unloading module comprises a time synchronization component and a data container component, and the logical relationship is as follows: in order to avoid the problem caused by different sending periods of different sensors, a time synchronization component is called to perform time synchronization processing on lane line offline data in each first data container and load a timestamp, the data container component adds corresponding sensor zone bits to each data subjected to time synchronization, and then all first data containers A subjected to sensor zone bit addition1And transferring all lane line offline data in the data to An to a second data container B. In order to adapt to the requirements of different analysts, the data unloading module is provided with an interface separately, and if the data in the second data container B needs to be cleaned, the analysts only need to use the interface to load the screening rule to finally obtain the required data.
A time flow graph module: and extracting the target lane line offline data of all the sensors in the target time period from the second data container according to the target time period and the target lane line coefficient to be displayed, which are selected by a developer in advance. And respectively establishing a Cartesian coordinate system with the horizontal axis as time and the vertical axis as a target lane curve coefficient for each sensor to form a first curve graph of each target lane curve coefficient of each sensor along with time change in the target time period.
Specifically, the time flow graph module: mainly comprises 2 components, a time window component and a drawing component. The logical relationship is as follows: the developer selects a specific target time period in advance, and all lane line offline data streams containing the target time period flow into the time window component in series. The time window component is called to enable lane line off-line data flow to establish a first curve graph which takes x as time and y axis as the numerical value of the corresponding target lane line parameter under a Cartesian coordinate system, dynamically display the numerical value of the corresponding target lane line at each moment, and enable analysts to visually observe the change of signals.
The drawing component leaves a calling interface for subsequent visualization.
A numerical analysis module: and processing the coefficients according to the target lane line selected by the developer and the corresponding statistical method, mean, expectation and variance selected by the developer and transmitting the coefficients to a visualization module.
Specifically, the numerical analysis module is mainly composed of statistical algorithm components, and an interface is reserved to facilitate an analyst to add a new statistical method. The module mainly comprises 2 components, a statistical algorithm component (a mean component, a variance component and an expectation component) and a drawing component. The statistical algorithm component is used for calculating the mean value, the expectation and the variance of each target lane curve coefficient of each sensor based on a first graph of each target lane curve coefficient of each sensor changing along with time in the target time period, and then drawing by using the drawing component to form a second graph of the mean value of each target lane curve coefficient of each sensor changing along with time in the target time period, a third graph of the variance of each target lane curve coefficient of each sensor changing along with time in the target time period, and/or a fourth graph of each target lane curve coefficient of each sensor changing along with time in the target time period.
The visualization module has the following functions: 1. providing a file loading interface and starting each module thread; 2. and displaying the results processed by the time flow graph unloading component and the numerical analysis component on an interface through the data volume. 3. The original video image is displayed.
The visualization module mainly comprises 2 components, a thread component and a user interface component. The thread components respectively serve the 4 modules, and the starting of four different threads is respectively as follows: the system comprises an offline data analysis and data unloading thread, a time flow graph thread, a numerical analysis thread and an original video thread. And the user interface components are used for respectively providing controls for the threads to trigger the signal slot function to open the threads, and are also provided with two terminals for displaying drawing.
The above-described apparatus in this embodiment will now be described with reference to examples:
in the embodiment, the automatic driving data packet recorded by the CAN protocol comprises forward-looking camera Lane line information and all-round-looking camera Lane line information, and is replaced by FC _ Lane and SC _ Lane respectively.
1. A visualization module: and leading in a lane line offline data packet to be analyzed in a data loading window by an analyst, and calling an offline data analysis thread, a data unloading thread, a time flow graph thread and a numerical analysis thread to complete initialization. And (5) receiving the output results of the following steps 4 and 5 by using an interface, and visually displaying the output results according to the sensor types.
2. An offline data analysis module: and importing data to the data loading component according to the data path provided in the step 1, and resolving the SC _ Lane and FC _ Lane signals in 40ms (period) by the resolving component according to the communication matrix and storing the signals into the first data containers A1 and A2 respectively.
3. Data cleaning and unloading: firstly, data in the second data containers A1 and A2 are synchronized according to the current time of the system (time synchronization is to ensure that the received sensors ensure the same time), and then SC \ FC sensor flag bits are respectively added to lane line offline data in the forward-looking cameras A1 and the around-looking cameras A2 and stored in the second data container B.
4. A time flow graph module: extracting three-time curve coefficients FC \ SC _ lane _ C0\ C2\ C3 in the second data container B, wherein the three-time curve coefficients are respectively three signal input quantities, the three signal input quantities are drawn in a visualization component by a Cartesian coordinate system Y value and a timestamp is an X axis, and the signal change can be dynamically displayed along with the time change;
5. a numerical analysis module: and extracting FC \ SC _ lane _ C0\ C2\ C3 coefficients in the second data container B to respectively carry out statistic (mean value and variance) iterative calculation, and displaying statistic values in a visualization module according to time flow in real time.
By the method, the lane line offline data can be visually analyzed, developers are helped to quickly and visually locate problems from the mass lane line offline data, the processing effect is improved, and the problem processing time is shortened.
Claims (2)
1. A lane line offline data visualization method is characterized by comprising the following steps:
acquiring and analyzing lane line offline data packets of each lane line sensor to obtain lane line offline data of each lane line sensor, and storing the lane line offline data of each sensor into a first data container respectively;
time synchronization is carried out on the lane line offline data of each sensor stored in each first data container, and then the lane line offline data of each sensor stored in each first data container after time synchronization is respectively added with the corresponding sensor zone bit and then is transferred into the same second data container;
selecting a target time period and a target lane line coefficient to be displayed, and extracting the target lane line offline data of all the sensors in the target time period from the second data container;
respectively establishing a Cartesian coordinate system with time as a horizontal axis and target lane curve coefficients as a vertical axis for each sensor to form a first curve graph of each target lane curve coefficient of each sensor along with time change in the target time period;
calculating a second plot of a mean of the target lane line curve coefficients of each sensor over time over the target time period, a third plot of a variance of the target lane line curve coefficients of each sensor over time over the target time period, and/or a fourth plot of the target lane line curve coefficients of each sensor expected to vary over time over the target time period, based on the first plot of the target lane line curve coefficients of each sensor over time over the target time period;
and carrying out output display on a second graph of the mean value of the target lane curve coefficients of each sensor changing along with time in the target time period, a third graph of the variance of the target lane curve coefficients of each sensor changing along with time in the target time period, and/or a fourth graph of the target lane curve coefficients of each sensor expected to change along with time in the target time period.
2. An apparatus for visualizing lane line offline data, the apparatus comprising:
the off-line data analysis module is used for acquiring and analyzing lane line off-line data packets of each lane line sensor to obtain lane line off-line data of each lane line sensor, and then storing the lane line off-line data of each sensor into a first data container;
the data unloading module is used for carrying out time synchronization on the lane line offline data of each sensor stored in each first data container, and unloading the lane line offline data of each sensor stored in each first data container after time synchronization into the same second data container after adding the corresponding sensor flag bit to the lane line offline data of each sensor stored in each first data container;
the time flow graph module is used for selecting a target time period and a target lane line coefficient to be displayed, and extracting the target lane line offline data of all the sensors in the target time period from the second data container; respectively establishing a Cartesian coordinate system with time as a horizontal axis and target lane curve coefficients as a vertical axis for each sensor to form a first curve graph of each target lane curve coefficient of each sensor along with time change in the target time period;
a numerical analysis module for calculating a second graph of a mean of the target lane line curve coefficients of each sensor over time within the target time period, a third graph of a variance of the target lane line curve coefficients of each sensor over time within the target time period, and/or a fourth graph of the target lane line curve coefficients of each sensor expected to change over time within the target time period, based on the first graph of the target lane line curve coefficients of each sensor over time within the target time period;
and the visualization module is used for outputting and displaying a second curve graph of the mean value of the target lane curve coefficients of each sensor, a third curve graph of the variance of the target lane curve coefficients of each sensor, and/or a fourth curve graph of the target lane curve coefficients of each sensor, which is expected to change along with time in the target time period, in the target time period.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111158760.1A CN113886634B (en) | 2021-09-30 | 2021-09-30 | Lane line offline data visualization method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111158760.1A CN113886634B (en) | 2021-09-30 | 2021-09-30 | Lane line offline data visualization method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113886634A true CN113886634A (en) | 2022-01-04 |
CN113886634B CN113886634B (en) | 2024-04-12 |
Family
ID=79004541
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111158760.1A Active CN113886634B (en) | 2021-09-30 | 2021-09-30 | Lane line offline data visualization method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113886634B (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102034284A (en) * | 2010-09-28 | 2011-04-27 | 魏卿轩 | Device for recording real-time controlled cooling temperature curve graph of steel on controlled cooling line after hot rolling |
DE102016212326A1 (en) * | 2016-07-06 | 2018-01-11 | Robert Bosch Gmbh | Method for processing sensor data for a position and / or orientation of a vehicle |
CN109982426A (en) * | 2019-03-21 | 2019-07-05 | 中国科学院合肥物质科学研究院 | A kind of automatic driving vehicle sensing data offline synchronization method |
EP3637311A1 (en) * | 2018-10-10 | 2020-04-15 | ZF Friedrichshafen AG | Device and method for determining the altitude information of an object in an environment of a vehicle |
CN112284416A (en) * | 2020-10-19 | 2021-01-29 | 武汉中海庭数据技术有限公司 | Automatic driving positioning information calibration device, method and storage medium |
CN113436190A (en) * | 2021-07-30 | 2021-09-24 | 重庆长安汽车股份有限公司 | Lane line quality calculation method and device based on lane line curve coefficient and automobile |
CN113432615A (en) * | 2021-07-31 | 2021-09-24 | 重庆长安汽车股份有限公司 | Detection method and system based on multi-sensor fusion drivable area and vehicle |
-
2021
- 2021-09-30 CN CN202111158760.1A patent/CN113886634B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102034284A (en) * | 2010-09-28 | 2011-04-27 | 魏卿轩 | Device for recording real-time controlled cooling temperature curve graph of steel on controlled cooling line after hot rolling |
DE102016212326A1 (en) * | 2016-07-06 | 2018-01-11 | Robert Bosch Gmbh | Method for processing sensor data for a position and / or orientation of a vehicle |
EP3637311A1 (en) * | 2018-10-10 | 2020-04-15 | ZF Friedrichshafen AG | Device and method for determining the altitude information of an object in an environment of a vehicle |
CN109982426A (en) * | 2019-03-21 | 2019-07-05 | 中国科学院合肥物质科学研究院 | A kind of automatic driving vehicle sensing data offline synchronization method |
CN112284416A (en) * | 2020-10-19 | 2021-01-29 | 武汉中海庭数据技术有限公司 | Automatic driving positioning information calibration device, method and storage medium |
CN113436190A (en) * | 2021-07-30 | 2021-09-24 | 重庆长安汽车股份有限公司 | Lane line quality calculation method and device based on lane line curve coefficient and automobile |
CN113432615A (en) * | 2021-07-31 | 2021-09-24 | 重庆长安汽车股份有限公司 | Detection method and system based on multi-sensor fusion drivable area and vehicle |
Non-Patent Citations (2)
Title |
---|
A SARKER等: "A review of sensing and communication, human factors, and controller aspects for information-aware connected and automated vehicles", 《IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS》, vol. 21, no. 1, 15 March 2019 (2019-03-15), pages 7 - 29 * |
白悦章: "基于多传感器融合的目标追踪与定位估计技术研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》, no. 12, 15 December 2019 (2019-12-15), pages 140 - 136 * |
Also Published As
Publication number | Publication date |
---|---|
CN113886634B (en) | 2024-04-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109086668B (en) | Unmanned aerial vehicle remote sensing image road information extraction method based on multi-scale generation countermeasure network | |
CN108550258B (en) | Vehicle queuing length detection method and device, storage medium and electronic equipment | |
CN108664841A (en) | A kind of sound state object recognition methods and device based on laser point cloud | |
CN112396093B (en) | Driving scene classification method, device and equipment and readable storage medium | |
CN107977654B (en) | Road area detection method, device and terminal | |
CN112949782A (en) | Target detection method, device, equipment and storage medium | |
CN111695619A (en) | Multi-sensor target fusion method and device, vehicle and storage medium | |
US10962380B2 (en) | Analysis of network effects of avoidance areas on routing | |
CN110083099B (en) | Automatic driving architecture system meeting automobile function safety standard and working method | |
CN113610143B (en) | Method, device, equipment and storage medium for classifying point cloud noise points | |
CN113771573A (en) | Vehicle suspension control method and device based on road surface identification information | |
CN111488808A (en) | Lane line detection method based on traffic violation image data | |
CN113781767A (en) | Traffic data fusion method and system based on multi-source perception | |
CN113643431A (en) | System and method for iterative optimization of visual algorithm | |
CN110111018B (en) | Method, device, electronic equipment and storage medium for evaluating vehicle sensing capability | |
CN111009136A (en) | Method, device and system for detecting vehicles with abnormal running speed on highway | |
CN114972758A (en) | Instance segmentation method based on point cloud weak supervision | |
CN113886634B (en) | Lane line offline data visualization method and device | |
CN117518189A (en) | Laser radar-based camera processing method and device, electronic equipment and medium | |
CN113895449B (en) | Forward target determination method and device and electronic equipment | |
CN114356931A (en) | Data processing method, data processing device, storage medium, processor and electronic device | |
KR20230104592A (en) | Method and system for annotating sensor data | |
CN112598314A (en) | Method, device, equipment and medium for determining perception confidence of intelligent driving automobile | |
CN112147602A (en) | Road edge identification method and system based on laser point cloud | |
CN113158864B (en) | Method and device for determining included angle between truck head and trailer |
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 |