A Method of Vehicle Motion State Estimation with Guaranteed Accuracy

A motion state and accuracy technology, applied in computing, image analysis, instruments, etc., can solve the problem of low accuracy of vehicle motion state

Active Publication Date: 2019-07-16
NANJING UNIV OF POSTS & TELECOMM
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is: Aiming at the problem that the accuracy of obtaining the current vehicle motion state online from vehicle-mounted video data is not high, a method for estimating the vehicle motion state with guaranteed accuracy is proposed. accuracy of results

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 of Vehicle Motion State Estimation with Guaranteed Accuracy
  • A Method of Vehicle Motion State Estimation with Guaranteed Accuracy
  • A Method of Vehicle Motion State Estimation with Guaranteed Accuracy

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0083] Below in conjunction with accompanying drawing, technical scheme of the present invention is described in further detail:

[0084] The present invention proposes a vehicle motion state estimation method that guarantees accuracy. It consists of three parts: feature extraction, data analysis, and result verification. Feature point pairs are extracted through a bidirectional optical flow algorithm, and a combination of random sampling consensus algorithm and eight-point algorithm is used to iterate. Solve the basic matrix to obtain the motion direction vector and rotation matrix, and verify the final result according to the vehicle's own motion path constraints. The feature extraction part of the algorithm uses a two-way optical flow algorithm to ensure the reliability of the obtained feature point pairs and filter noise data. The data analysis part adopts the combination of random sampling consensus algorithm and eight-point algorithm, sorts the obtained basic matrix acco...

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 a vehicle motion state estimation method capable of ensuring accuracy, which comprises three parts of feature extraction, data analysis and result validation. In the feature extraction part, a bidirectional optical flow algorithm is adopted to ensure the reliability of obtained feature point pairs, and noise data are filtered. In the data analysis part, a random sampling consensus algorithm and an eight-point algorithm are adopted, obtained basic matrixes are ranked from high to low based on the matching degrees towards the whole feature point pair set, and a corresponding motion direction vector and a rotation matrix are solved. In the result validation part, the solved motion direction vector and the rotation matrix are validated, and rationality of the final result is ensured. Constraint conditions of a translation vector and a rotation matrix can be considered, the result accuracy is thus improved, certain calculation efficiency is ensured, data processing is carried out on the premise of ensuring the efficiency, and online analysis on video data is realized.

Description

technical field [0001] The invention relates to a method for estimating the motion state of a vehicle with guaranteed accuracy, and belongs to the cross-technical application fields of computer vision, video mining and computer software. Background technique [0002] Vehicle unmanned driving needs to process the video data to obtain the current position and trajectory of the vehicle. Accurate acquisition of vehicle state parameters is an important requirement to ensure the effectiveness of the vehicle's active safety system. Carry out kinematics or dynamics modeling on the motion process of the vehicle, and use the information of the corresponding on-board sensors (such as wheel speed sensors, gyroscopes, accelerometers, etc.) State estimates. This method needs to model the vehicle as a whole or even each tire separately. When these models or model parameters are inaccurate, the estimation error will be large. [0003] With the continuous development of computer software 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
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/207G06T7/246
CPCG06T7/207G06T7/246
Inventor 张帅岳文静陈志白园
Owner NANJING UNIV OF POSTS & TELECOMM
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