CN108052564A - A kind of method and system for establishing unmanned database - Google Patents

A kind of method and system for establishing unmanned database Download PDF

Info

Publication number
CN108052564A
CN108052564A CN201711274645.4A CN201711274645A CN108052564A CN 108052564 A CN108052564 A CN 108052564A CN 201711274645 A CN201711274645 A CN 201711274645A CN 108052564 A CN108052564 A CN 108052564A
Authority
CN
China
Prior art keywords
data
vehicle
database
unmanned
camera
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
Application number
CN201711274645.4A
Other languages
Chinese (zh)
Inventor
漆进
史鹏
张通
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
University of Electronic Science and Technology of China
Original Assignee
University of Electronic Science and Technology of China
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by University of Electronic Science and Technology of China filed Critical University of Electronic Science and Technology of China
Priority to CN201711274645.4A priority Critical patent/CN108052564A/en
Publication of CN108052564A publication Critical patent/CN108052564A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01SRADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S13/00Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
    • G01S13/86Combinations of radar systems with non-radar systems, e.g. sonar, direction finder
    • G01S13/867Combination of radar systems with cameras
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01SRADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S13/00Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
    • G01S13/88Radar or analogous systems specially adapted for specific applications
    • G01S13/93Radar or analogous systems specially adapted for specific applications for anti-collision purposes
    • G01S13/931Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/901Indexing; Data structures therefor; Storage structures
    • G06F16/9027Trees

Landscapes

  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • Databases & Information Systems (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Software Systems (AREA)
  • Electromagnetism (AREA)
  • Traffic Control Systems (AREA)

Abstract

The present invention provides a kind of method and system for establishing unmanned database.This method includes:Acquisition to laser radar data, millimetre-wave radar, camera, on-vehicle information data;The foundation of data acquisition hardware system;The foundation of data acquisition software system.This invention ensures that the real-time and synchronism of data information acquisition, therefore, have wide range of applications.

Description

A kind of method and system for establishing unmanned database
Technical field
The present invention relates to unmanned fields, more particularly, to a kind of method for establishing unmanned database and are System.
Background technology
Since second industrial revolution, automobile industry has been developed more than 100 years.In past more than 100 years, as The important symbol of modern civilization, automobile have overturned the life style of the mankind, have expanded the activity space of the mankind, change entire society Meeting form greatly improves the movable living quality of the mankind, but automobile, which needs driver to drive, to travel, and occupy excessive Human resources, and substantial amounts of traffic accident is caused, with the development of depth learning technology, unmanned technology is like a raging fire to be opened Exhibition is got up.
Pilotless automobile research extremely relies on the truthful data of a large amount of high quality, because it is needed before public way deployment Exploitation, test and verification algorithm.It is unmanned to have a series of automatic Pilot data set of view-based access control models at present in the industry, wherein Including KITTI and Citycapes data sets.KITTI data sets are a cooperation item 2012 by KIT and TTIC Mesh, website is in http://www.cvlibs.net/datasets/kitti/, the main purpose of this project are to establish a tool Test set challenging, from real world.The RobotCar data sets that Oxonian researcher releases. The RobotCar data sets data sets includes the repetition driving data that ride 100 times is fixed in England Oxford city in 1 year. The data set captures many different weather, traffic, the road conditions of pedestrian's combination out, also comprising building and road construction so Change in long term.
Using international data center, academic research can only be carried out, can not be applied on engineering, so needing suggestion The database of team oneself demand so far, still establishes unmanned database without disclosed method.It consults related special Profit, the domestic patent on unmanned Database not yet is because rare team has the ability to develop with financial resources and maintain One applicable unmanned data acquisition platform, periodic calibration simultaneously collect new data.
The content of the invention
The technical problem to be solved in the present invention is to provide a kind of method for establishing unmanned database, comprising unmanned Database acquisition hardware system and unmanned database acquisition software system, can be in state by the combination of software and hardware system Unmanned database is established on interior any road, further, unmanned correlation technique can be carried out on this database Research.
The technical solution used in the present invention is:A kind of method for establishing unmanned database, comprises the following steps,
(1) unmanned database acquisition hardware system is established, laser radar, camera, millimeter wave are installed on the car body Radar and CAN analyzers, while a vehicle-mounted computer is installed;Laser radar is communicated by UDP (User Datagram Protocol), ether Network interface is connected on vehicle-mounted computer;Camera is connected to vehicle-mounted computer by USB (universal serial bus);Millimetre-wave radar leads to CAN (controller local area network) agreement is crossed, vehicle-mounted computer is connected to using CAN analyzers;On-vehicle information (speed, vehicle corner etc.) CAN analyzers are connected to by the CBD interfaces of automobile itself;
(2) using ad hoc fashion Calibration of Laser radar and camera, their imaging coordinate system relations, the ginseng that will be obtained are obtained Number is inputted to unmanned database software acquisition system;
(3) the on-vehicle information decoding process of vehicle is inputted to unmanned database acquisition software system, it will obtain The information of vehicles such as correct speed, vehicle corner, vehicle acceleration
(4) unmanned database acquisition software system is run, which can receive, parse, storing four automatically Sensing data:Laser radar data, millimetre-wave radar data, camera data, on-vehicle information;Ensure gathered data simultaneously Synchronism and real-time can accomplish the picking rate of 10fps;
Operating and controlling vehicle is multiple in target road traveling in turn for (5) 20 experienced drivers, the acquisition period need to be related to daytime, Night, various weather conditions, time in the four seasons;In the process of moving, unmanned database acquisition hardware system and software systems It works at the same time.
Further, the vehicle-mounted computer include a 3G dominant frequency CPU, 4G memory, a 220V electric pressure converter, one Power interface, a network interface, two USB ports and a 1T mechanical hard disk.
Further, the laser radar is containing 32 laser emitter/receivers, distance range 1-70m, distance point Resolution is less than 2cm;Laser radar supply voltage is 220V, and a 48V-220V inverter is accessed from vehicle itself accumulator, is Laser radar and the power supply of vehicle-mounted brain.
Further, the CAN analyzers contain 2 CAN passages, with CAN protocol function interface storehouse;The camera Possess 200W pixels for USB interface.
Further, the ad hoc fashion Calibration of Laser radar and camera are to use the chessboard mark in KITTI databases Determine the relation that method obtains laser infrared radar imaging coordinate system and camera coordinate system.
Further, the unmanned database acquisition software system includes five parts:Laser radar data receives Parsing part, millimetre-wave radar data receiver and parsing, on-vehicle information data receiver and parsing part, camera image reading part Divide, data storage section after parsing.
Further, the synchronism of the gathered data refers to:Laser radar data, millimetre-wave radar data, vehicle-mounted letter Data and camera image data acquisition are ceased in synchronization, remains to synchronism, and the cooperation between data is just significant.
Further, the real-time of the gathered data refers to:Laser radar data, millimetre-wave radar data, vehicle-mounted letter Time spent by the process that breath data are stored with camera image data from sensor to data is small, keeps all modules Data be all current time newest data.
Due to the adoption of the above technical scheme, advantageous effect caused by the present invention is:
(1) it is of the present invention to establish unmanned data base method, it can be fitted in modification software systems Program on a small quantity It, can the operation in wind and rain weather for any manufacturer's vehicle.
(2) it is of the present invention to establish unmanned data base method, it can completely establish a set of unmanned data Storehouse,
It is applicable to a variety of actual scenes such as unmanned middle speed decision-making, obstacle judgement, lane detection.
Description of the drawings
Fig. 1:Unmanned database file storage organization
Fig. 2:Unmanned database acquisition software system program flow chart
Specific embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, with reference to the accompanying drawings and embodiments, it is right The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and It is not used in the restriction present invention:
(1) unmanned database acquisition hardware system is established, laser radar, camera, millimeter wave are installed on the car body Radar and CAN analyzers, while a vehicle-mounted computer is installed;Laser radar is communicated by UDP (User Datagram Protocol), with Too network interface is connected on vehicle-mounted computer;Camera is connected to vehicle-mounted computer by USB (universal serial bus);Millimetre-wave radar By CAN (controller local area network) agreement, vehicle-mounted computer is connected to using CAN analyzers;On-vehicle information (speed, vehicle corner Deng) CAN analyzers are connected to by the CBD interfaces of automobile itself;
(2) using ad hoc fashion Calibration of Laser radar and camera, their imaging coordinate system relations, the ginseng that will be obtained are obtained Number is inputted to unmanned database software acquisition system;
(3) the on-vehicle information decoding process of vehicle is inputted to unmanned database acquisition software system, it will obtain The information of vehicles such as correct speed, vehicle corner, vehicle acceleration
(4) unmanned database acquisition software system is run, which can receive, parse, storing four automatically Sensing data:Laser radar data, millimetre-wave radar data, camera data, on-vehicle information;Ensure gathered data simultaneously Synchronism and real-time can accomplish the picking rate of 10fps;
Operating and controlling vehicle is multiple in target road traveling in turn for (5) 20 experienced drivers, the acquisition period need to be related to daytime, Night, various weather conditions, time in the four seasons;In the process of moving, unmanned database acquisition hardware system and software systems It works at the same time.
Further, the vehicle-mounted computer include a 3G dominant frequency CPU, 4G memory, a 220V electric pressure converter, one Power interface, a network interface, two USB ports and a 1T mechanical hard disk.
Further, the laser radar is containing 32 laser emitter/receivers, distance range 1-70m, distance point Resolution is less than 2cm;Laser radar supply voltage is 220V, and a 48V-220V inverter is accessed from vehicle itself accumulator, is Laser radar and the power supply of vehicle-mounted brain.
Further, the CAN analyzers contain 2 CAN passages, with CAN protocol function interface storehouse;The camera Possess 200W pixels for USB interface.
Further, the ad hoc fashion Calibration of Laser radar and camera are to use the chessboard mark in KITTI databases Determine the relation that method obtains laser infrared radar imaging coordinate system and camera coordinate system.
Further, the unmanned database acquisition software system includes five parts:Laser radar data receives Parsing part, millimetre-wave radar data receiver and parsing, on-vehicle information data receiver and parsing part, camera image reading part Divide, data storage section after parsing.
Further, the synchronism of the gathered data refers to:Laser radar data, millimetre-wave radar data, vehicle-mounted letter Data and camera image data acquisition are ceased in synchronization, remains to synchronism, and the cooperation between data is just significant.
Further, the real-time of the gathered data refers to:Laser radar data, millimetre-wave radar data, vehicle-mounted letter Time spent by the process that breath data are stored with camera image data from sensor to data is small, keeps all modules Data be all current time newest data.
The above-described embodiments are merely illustrative of preferred embodiments of the present invention, not to the structure of the present invention Think and scope is defined.On the premise of design concept of the present invention is not departed from, ordinary people in the field is to the technology of the present invention The all variations and modifications that scheme is made, should all drop into protection scope of the present invention, the claimed technology contents of the present invention, All it is documented in claims.

Claims (8)

1. a kind of method and system for establishing unmanned database, which is characterized in that comprise the following steps,
(1) unmanned database acquisition hardware system is established, laser radar, camera, millimetre-wave radar are installed on the car body With CAN analyzers, while install a vehicle-mounted computer;Laser radar is communicated by UDP (User Datagram Protocol), and Ethernet connects Mouth is connected on vehicle-mounted computer;Camera is connected to vehicle-mounted computer by USB (universal serial bus);Millimetre-wave radar passes through CAN (controller local area network) agreement, vehicle-mounted computer is connected to using CAN analyzers;On-vehicle information (speed, vehicle corner etc.) is logical The CBD interfaces for crossing automobile itself are connected to CAN analyzers;
(2) using ad hoc fashion Calibration of Laser radar and camera, their imaging coordinate system relations are obtained, obtained parameter is defeated Enter to unmanned database software acquisition system;
(3) the on-vehicle information decoding process of vehicle is inputted to unmanned database acquisition software system, it will obtain correct The information of vehicles such as speed, vehicle corner, vehicle acceleration;
(4) unmanned database acquisition software system is run, which can receive, parse, storing four sensings automatically Device data:Laser radar data, millimetre-wave radar data, camera data, on-vehicle information;Ensure the synchronization of gathered data simultaneously Property and real-time can accomplish the picking rate of 10fps;
Operating and controlling vehicle is multiple in target road traveling in turn for (5) 20 experienced drivers, and the acquisition period needs to be related to daytime, black Night, various weather conditions, time in the four seasons;In the process of moving, unmanned database acquisition hardware system and software systems are same When work.
2. the method and system according to claim 1 for establishing unmanned database, which is characterized in that the step (1) vehicle-mounted computer in include a 3G dominant frequency CPU, 4G memory, a 220V electric pressure converter, a power interface, one Network interface, two USB ports and a 1T mechanical hard disk.
3. the method and system according to claim 1 for establishing unmanned database, which is characterized in that the step (1) laser radar in, containing 32 laser emitter/receivers, distance range 1-70m, distance resolution is less than 2cm;Swash Optical radar supply voltage is 220V, and a 48V-220V inverter is accessed from vehicle itself accumulator, is laser radar and vehicle-mounted Brain is powered.
4. the method and system according to claim 1 for establishing unmanned database, which is characterized in that the step (1) the CAN analyzers in contain 2 CAN passages, with CAN protocol function interface storehouse;The camera is gathered around for USB interface There are 200W pixels.
5. the method and system according to claim 1 for establishing unmanned database, which is characterized in that the step (2) in, ad hoc fashion Calibration of Laser radar and camera refer to obtain laser using the chessboard calibration method in KITTI databases The relation of radar imagery coordinate system and camera coordinate system.
6. the method and system according to claim 1 for establishing unmanned database, which is characterized in that the step (4) in, unmanned database acquisition software system includes five parts:Laser radar data receives parsing part, millimeter wave Radar data is received to be deposited with parsing, on-vehicle information data receiver and data after parsing part, camera image reading part, parsing Store up part.
7. the method and system according to claim 1 for establishing unmanned database, which is characterized in that the step (4) in, the synchronism of gathered data refers to:Laser radar data, millimetre-wave radar data, on-vehicle information data and camera figure As data acquisition is in synchronization, synchronism is remained to, the cooperation between data is just significant.
8. the method and system according to claim 1 for establishing unmanned database, which is characterized in that the step (4) in, the real-time of gathered data refers to:Laser radar data, millimetre-wave radar data, on-vehicle information data and camera figure The time as spent by the process that data are stored from sensor to data is small, when the data of all modules being kept all to be current Carve newest data.
CN201711274645.4A 2017-12-06 2017-12-06 A kind of method and system for establishing unmanned database Pending CN108052564A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201711274645.4A CN108052564A (en) 2017-12-06 2017-12-06 A kind of method and system for establishing unmanned database

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201711274645.4A CN108052564A (en) 2017-12-06 2017-12-06 A kind of method and system for establishing unmanned database

Publications (1)

Publication Number Publication Date
CN108052564A true CN108052564A (en) 2018-05-18

Family

ID=62121652

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201711274645.4A Pending CN108052564A (en) 2017-12-06 2017-12-06 A kind of method and system for establishing unmanned database

Country Status (1)

Country Link
CN (1) CN108052564A (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109085829A (en) * 2018-08-09 2018-12-25 北京智行者科技有限公司 A kind of sound state target identification method
CN109094574A (en) * 2018-08-01 2018-12-28 长安大学 A kind of unmanned vehicle driving condition Measurement and Control System based on rack
CN110009765A (en) * 2019-04-15 2019-07-12 合肥工业大学 A kind of automatic driving vehicle contextual data system and scene format method for transformation
CN111376851A (en) * 2018-12-29 2020-07-07 浙江吉利控股集团有限公司 Automobile positioning system and method and automobile
CN114755673A (en) * 2020-12-25 2022-07-15 欧特明电子股份有限公司 Multi-sensor automatic driving system

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130144521A1 (en) * 2011-12-02 2013-06-06 GM Global Technology Operations LLC Optimum driving path on full windshield display
CN105388021A (en) * 2015-10-21 2016-03-09 重庆交通大学 ADAS virtual development and test system
CN105823478A (en) * 2016-03-14 2016-08-03 武汉卓拔科技有限公司 Autonomous obstacle avoidance navigation information sharing and using method

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130144521A1 (en) * 2011-12-02 2013-06-06 GM Global Technology Operations LLC Optimum driving path on full windshield display
CN105388021A (en) * 2015-10-21 2016-03-09 重庆交通大学 ADAS virtual development and test system
CN105823478A (en) * 2016-03-14 2016-08-03 武汉卓拔科技有限公司 Autonomous obstacle avoidance navigation information sharing and using method

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
高洁: "无人车平台立体视觉技术研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 *

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109094574A (en) * 2018-08-01 2018-12-28 长安大学 A kind of unmanned vehicle driving condition Measurement and Control System based on rack
CN109094574B (en) * 2018-08-01 2021-06-25 长安大学 Unmanned vehicle driving state measurement control system based on rack
CN109085829A (en) * 2018-08-09 2018-12-25 北京智行者科技有限公司 A kind of sound state target identification method
CN109085829B (en) * 2018-08-09 2022-03-08 北京智行者科技有限公司 Dynamic and static target identification method
CN111376851A (en) * 2018-12-29 2020-07-07 浙江吉利控股集团有限公司 Automobile positioning system and method and automobile
CN110009765A (en) * 2019-04-15 2019-07-12 合肥工业大学 A kind of automatic driving vehicle contextual data system and scene format method for transformation
CN110009765B (en) * 2019-04-15 2021-05-07 合肥工业大学 Scene format conversion method of automatic driving vehicle scene data system
CN114755673A (en) * 2020-12-25 2022-07-15 欧特明电子股份有限公司 Multi-sensor automatic driving system

Similar Documents

Publication Publication Date Title
CN108052564A (en) A kind of method and system for establishing unmanned database
CN111859618B (en) Virtual-real combined traffic comprehensive scene simulation test system and method for multi-terminal ring
JP7070974B2 (en) Sparse map for autonomous vehicle navigation
CN108959321B (en) Parking lot map construction method, system, mobile terminal and storage medium
CN107246868B (en) Collaborative navigation positioning system and navigation positioning method
CN107229690B (en) Dynamic High-accuracy map datum processing system and method based on trackside sensor
CN104002747B (en) A kind of multilasered optical radar grating map emerging system based on intelligent car
CN111473980B (en) Intelligent automobile automatic driving capability test system
EP3647734A1 (en) Automatic generation of dimensionally reduced maps and spatiotemporal localization for navigation of a vehicle
US20160210775A1 (en) Virtual sensor testbed
US11042758B2 (en) Vehicle image generation
CN106969779A (en) Intelligent vehicle map emerging system and method based on DSRC
CN106198049A (en) Real vehicles is at ring test system and method
CN113962141A (en) Target detection model automatic iteration method, device and storage medium
CN110298311B (en) Method and device for detecting surface water accumulation
Li et al. Integration of vision and topological self-localization for intelligent vehicles
Lee et al. Building a V2X simulation framework for future autonomous driving
CA3136909A1 (en) Systems and methods for simultaneous localization and mapping using asynchronous multi-view cameras
CN111477030A (en) Vehicle collaborative risk avoiding method, vehicle end platform, cloud end platform and storage medium
CN117056153A (en) Methods, systems, and computer program products for calibrating and verifying driver assistance systems and/or autopilot systems
CN116597690B (en) Highway test scene generation method, equipment and medium for intelligent network-connected automobile
Shangguan et al. Interactive perception-based multiple object tracking via CVIS and AV
CN116917828A (en) Instantiating objects in a simulation environment based on log data
CN110332929A (en) Vehicle-mounted pedestrian positioning system and method
CN117950399A (en) Automatic obstacle avoidance decision method and system based on multi-mode knowledge graph

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
WD01 Invention patent application deemed withdrawn after publication
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20180518