Supercharge Your Innovation With Domain-Expert AI Agents!

A method for time alignment of multi-sensor data and data acquisition equipment

A data acquisition device and time alignment technology, applied in transmission systems, multiplexing communications, digital transmission systems, etc., can solve problems such as synchronization data errors, failure to meet the positioning accuracy of automatic driving, etc., and achieve the effect of improving multi-transmission

Active Publication Date: 2022-04-01
BEIJING MOMENTA TECH CO LTD
View PDF22 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in practice, it is found that the synchronization data obtained according to the above method actually still has certain errors. When using these data for vehicle positioning, it cannot meet the positioning accuracy required for automatic driving.

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
  • A method for time alignment of multi-sensor data and data acquisition equipment
  • A method for time alignment of multi-sensor data and data acquisition equipment
  • A method for time alignment of multi-sensor data and data acquisition equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0058] see figure 1 , figure 1 It is a schematic flowchart of a time alignment method for multi-sensor data disclosed in an embodiment of the present invention. Such as figure 1 As shown, the multi-sensor data method may include the following steps:

[0059] 101. The data collection device determines a reference sensor from multiple sensors.

[0060] In the embodiment of the present invention, the above-mentioned multiple sensors may include a camera, a satellite positioning device (such as a GPS device, a Beidou positioning device), an inertial navigation unit (Inertial measurement unit, IMU), a wheel speedometer, a radar, etc., the embodiment of the present invention No limit.

[0061] The transmission time required for the reference sensor to transmit data to the processor of the data acquisition device is greater than the transmission time required for any sensor other than the reference sensor to transmit data to the processor, that is, the reference sensor transmits ...

Embodiment 2

[0072] see figure 2 , figure 2 It is a schematic flowchart of a time alignment method for multi-sensor data disclosed in an embodiment of the present invention. Such as figure 2As shown, the multi-sensor data method may include the following steps:

[0073] 201. The data collection device determines a camera from multiple sensors as a reference sensor.

[0074] Among the multiple sensors mentioned above, the image data collected by the camera has a large amount of data and involves operations such as data encoding and decoding during transmission. The transmission time of image data is generally longer than that of other sensor data. Therefore, the camera can be determined as the reference sensor. With the camera as the reference sensor, visual information can be used as much as possible for data fusion, which can further improve the accuracy of data fusion. This is also one of the invention points of the present invention. In addition, by executing the following step...

Embodiment 3

[0102] see image 3 , image 3 It is a schematic structural diagram of a data acquisition device disclosed in an embodiment of the present invention. Such as image 3 As shown, the data acquisition equipment may include:

[0103] The selection unit 301 is configured to determine a reference sensor from the plurality of sensors, and the transfer time required for the reference sensor to transmit data to the processor is greater than the time required for any sensor in the plurality of sensors except the reference sensor to transmit data to the processor. the required transmission time;

[0104] In the embodiment of the present invention, the above-mentioned multiple sensors may include a camera, a satellite positioning device, an inertial navigation unit, a wheel speedometer, a radar, etc., which are not limited in the embodiment of the present invention.

[0105] A determination unit 302, configured to determine the difference between the transmission time of each sensor i...

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

A method for time alignment of multi-sensor data and a data acquisition device, the method comprising: determining a reference sensor from a plurality of sensors, and the transmission time required for the reference sensor to transmit data to a processor is the longest; The difference between the transmission time of each sensor other than the reference sensor and the transmission time of the reference sensor; for any target sensor except the reference sensor, use the difference corresponding to the target sensor to compare the first collection data collected by the reference sensor Correct the receiving time of the first collection data to obtain the new reception time of the first collection data, and determine the second collection data and the first collection data as synchronous data; the second collection data is the data collected by the target sensor, and the second collection data The receiving moment of is the same as the new receiving moment of the first collected data. This method can improve the time alignment accuracy of multi-sensor data, thereby unifying the environmental data collected by each sensor.

Description

technical field [0001] The invention relates to the technical field of automatic driving, in particular to a method for time alignment of multi-sensor data and a data acquisition device. Background technique [0002] In the technical solution of autonomous driving, a variety of different types of sensors are generally used for data collection, and these sensors perceive the surrounding environment of the autonomous vehicle independently of each other. Fusion of data collected by multiple sensors can more accurately perceive the surrounding environment and improve the safety of autonomous driving. However, each sensor can collect a large amount of data, so one of the prerequisites for data fusion is that a set of sensor data used for data fusion needs to be aligned in time. [0003] In order to perform time alignment between sensor data, generally when a data processing device (such as a central processing unit, Central Processing Unit, CPU) receives certain sensor data, the...

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 Patents(China)
IPC IPC(8): H04N5/04H04L7/00
CPCH04N5/04H04J3/0638H04L7/0016H04L7/00
Inventor 陈亮李晓东芦超辛梓
Owner BEIJING MOMENTA TECH CO LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More