Target-level multi-sensor fusion method of intelligent automobile
A multi-sensor fusion and smart car technology, applied in the field of sensor fusion, can solve problems such as repeated detection, target detection loss, and blind spots
Active Publication Date: 2020-12-04
JILIN UNIV
View PDF22 Cites 10 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Since each sensor has its own detection range, when it is arranged on the vehicle, it is inevitable that there will be overlapping detection areas or even blind areas, resulting in loss of target detection or repeated detection
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0063] The method of the present invention is realized by a target-level multi-sensor fusion system of a smart car, wherein a target-level multi-sensor fusion system of a smart car includes a coordinate conversion module, a time synchronization module, a target association module, a state estimation and New target generation module, track management module, target motion state prediction module and output management module;
[0064] The coordinate conversion module unifies the measurement values of the targets by each sensor into the vehicle coordinate system;
[0065] The time synchronization module inputs the longitudinal distance, relative longitudinal velocity, relative longitudinal acceleration, lateral distance, relative lateral velocity and relative lateral acceleration between the target and the vehicle in the vehicle coordinate system input by the coordinate conversion module at the time when the fusion center receives the sensor data Compensate for changes in the t...
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
Login to View More Abstract
The invention belongs to the technical field of sensor fusion, and particularly relates to a target-level multi-sensor fusion method of an intelligent automobile. The method comprises the following steps: carrying out space-time registration on target-level detection information, namely position, speed and acceleration information of a target, of the target by a plurality of sensors arranged on the intelligent automobile, carrying out global tracking on all targets detected by the plurality of sensors, fusing repeatedly detected targets to make a fusion center obtain continuous motion tracks of all targets in each sensor detection range, carrying out track management on all the targets, screening out alternative new targets in all the targets in the period after track management, that aretargets which are subjected to incomplete track generation and judgment, and taking the other targets and the motion states thereof as obstacle detection results of multi-sensor fusion finally outputby the fusion center in the current period. According to the invention, the targets around the vehicle can be stably and accurately detected and tracked, and the problems of repeated detection of thetargets in the overlapping detection area and the like can be avoided.
Description
technical field [0001] The invention belongs to the technical field of sensor fusion, and in particular relates to a target-level multi-sensor fusion method for an intelligent vehicle. Background technique [0002] With the rapid development of automobile intelligence and automation, the field of automobile autonomous driving technology has attracted more and more attention. Environmental perception is an important and indispensable link in the automatic driving of automobiles. In order to meet the needs of automatic driving of automobiles, the intelligent automobile environmental perception system needs to conduct comprehensive and accurate perception and detection of vehicles, pedestrians, bicycles and other objects in the traffic environment around the vehicle. probing. [0003] In order to meet the environmental perception requirements of autonomous driving, vehicles are often equipped with multiple or even multiple environmental sensors, such as millimeter-wave radar a...
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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G01C21/34G01S13/931G01S13/86G05D1/02
CPCG01C21/3415G01S13/931G01S13/86G05D1/0214
Inventor 蔡坤阳曲婷赖锋曲文奇高炳钊陈虹
Owner JILIN UNIV