Automatic driving data acquisition and fusion system and method

A technology for data acquisition and automatic driving, applied in radio wave measurement system, satellite radio beacon positioning system, radio wave reflection/re-radiation, etc., can solve problems such as clock error and time stamp information error, and avoid movement Distortion, high-precision synchronization, and hard synchronization

Pending Publication Date: 2022-01-04
万赛智能科技(苏州)有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, since the camera, millimeter-wave radar, and lidar have independent clocks, there are errors between the clocks, resulting in a relatively large error in the time stamp information of the collected data bands output by different sensors.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Automatic driving data acquisition and fusion system and method
  • Automatic driving data acquisition and fusion system and method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0044] Such as figure 1 As shown, a kind of automatic driving data acquisition and fusion system is disclosed, and the system includes:

[0045] A clock synchronization unit 11, an acquisition host 14 and at least two different types of sensor units.

[0046] The acquisition host is used for outputting control signals to the different types of sensors and the clock synchronization unit, and receiving the acquisition data with time stamps sent by the different types of sensors for data fusion.

[0047] Specifically, the acquisition host can output power-on and power-off signals so as to activate or deactivate the sensor, and can also set the working modes of the sensor and the clock synchronization unit. The data processed by the acquisition host can be transmitted to the disk 16 for storage for later application.

[0048] The clock synchronization unit is used to determine the current time according to the GNSS signal and provide time service to different types of sensors an...

Embodiment 2

[0052] The types of sensors in different scenarios can be set as required. In this embodiment, the different types of sensor units include at least one radar sensor 12 and at least one image acquisition sensor unit. Specifically, the radar sensor may be a laser radar and / or a millimeter-wave radar or the like.

[0053] Each of the radar sensors is used to scan the scene by rotating to collect corresponding point cloud data and send it to the collection host with a time stamp. The image acquisition sensor unit is used for image acquisition to obtain corresponding image data and send it to the acquisition host after adding a time stamp, so that the acquisition host can perform data fusion. In this application, the image acquisition sensor unit may include a camera, a camera, and the like.

[0054]Although the clock domains between the radar sensor and the image sensor have been synchronized through the settings in Embodiment 1, the data collected between the radar sensor and th...

Embodiment 3

[0060] In one frame of image, there are still thousands of rows of pixels, and the exposure time is different. When it is subsequently fused with the point cloud data of the lidar, a finer-grained matching cannot be achieved. For this reason, the image acquisition sensor unit in this application is also used to determine the exposure time of each row of pixels according to the image exposure time and the row pixels of each frame of image in the image data to determine each row of each frame of image in the image data Timestamp of the pixel;

[0061] The acquisition host is used to perform fusion according to the time stamp of each row of pixels of each frame image and the point cloud data carrying the time stamp.

[0062] Specifically, the unit exposure time of each row of pixels can be obtained by dividing the total exposure time of each frame of image by the number of row pixels, based on the initial exposure time of the image, the unit exposure time of each row of pixels, a...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses an automatic driving data acquisition and fusion system and method. The system comprises a clock synchronization unit, an acquisition host and at least two different types of sensor units; the acquisition host is used for outputting control signals to the sensors of different types and the clock synchronization unit and receiving acquisition data carrying timestamps sent by the sensors of different types for data fusion; the clock synchronization unit is used for determining the current time according to the GNSS signal and carrying out time service on different types of sensors; and the sensor units of different types are used for respectively acquiring data in the same scene and stamping timestamps on the acquired data according to the time service of the clock synchronization unit. The clock synchronization unit for determining the system time source by using the GNSS signal is added, and clock synchronization is performed on different sensors based on the time source, so that the data synchronism of the different sensors is improved.

Description

technical field [0001] This application belongs to the technical field of data collection and fusion, and specifically relates to a data collection and fusion system and method. Background technique [0002] In the process of realizing autonomous driving, vehicles often need to fuse data collected by multiple sensors to realize environmental perception and then make driving decisions. These sensors mainly include cameras, laser radars, millimeter-wave radars, and CAN sensors for collecting vehicle chassis. Together, they provide multi-dimensional perception data for autonomous driving to ensure the normal operation of autonomous driving. [0003] Data fusion needs to rely on time stamps. Specifically: each sensor works independently, and stamps the collected data with time stamps according to their respective clock signals, and sends the time stamps along with the collected data to the acquisition host for data fusion. The acquisition host fuses the data collected by each s...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G01S13/86G01S17/86G01S19/14
CPCG01S13/867G01S17/86G01S19/14
Inventor 董潇健黄毅
Owner 万赛智能科技(苏州)有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap