Unlock instant, AI-driven research and patent intelligence for your innovation.

Intersection vehicle state estimation algorithm based on UFIR filter

A vehicle state, intersection technology, applied in the field of estimation algorithms and signal processing, which can solve problems such as the limitations of collision estimation

Pending Publication Date: 2019-11-05
上海智驾汽车科技有限公司
View PDF6 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to provide a vehicle state estimation algorithm at an intersection based on UFIR filter, which solves the problem that the Kalman filter processing vehicle collision estimation has limitations in the prior art

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
  • Intersection vehicle state estimation algorithm based on UFIR filter
  • Intersection vehicle state estimation algorithm based on UFIR filter
  • Intersection vehicle state estimation algorithm based on UFIR filter

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] Below in conjunction with accompanying drawing, structure and working process of the present invention will be further described.

[0038] UFIR filtering algorithm is an estimation algorithm that coexists with Kalman filtering. Unlike Kalman filtering, UFIR does not require specific statistical characteristics (variance matrix) of process noise and measurement noise, so it can be applied to different intersections under different conditions. Collision speed estimation and trajectory restoration do not require trial and error and adjustment of parameters for specific application scenarios. And when the statistical properties of noise are unknown, UFIR filtering will get better estimation results than Kalman filtering. Therefore, the present invention proposes to improve the vehicle collision speed estimation and trajectory recovery algorithm based on the UFIR filter, and the specific process will be described in detail below.

[0039] A kind of intersection vehicle stat...

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 intersection vehicle state estimation algorithm based on a UFIR filter. The algorithm comprises the steps: firstly building a kinematic model of a vehicle in a vehicle collision process; secondly, calculating a parameter matrix of a UFIR filter according to the kinematic model of the vehicle; thirdly, extracting vehicle collision time information and vehicle position information with noise from the recorded image data; finally, conducting state estimation on the extracted information based on a UFIR filtering algorithm. The speed of the vehicle in the collision process is estimated. The track of the vehicle is restored. According to the method, vehicle collision speed estimation and track restoration are carried out in the noise environment based on the UFIR filtering algorithm. The statistical characteristics of noise and interference signals are not needed. Therefore, the method has universality and has good performance under the conditions of different intersections, different environments and different cameras.

Description

technical field [0001] The invention belongs to the field of estimation algorithms and signal processing, in particular to a UFIR filter-based intersection vehicle state estimation algorithm. Background technique [0002] It has important application value to estimate the vehicle collision speed and restore the trajectory from the monitoring image data after an accident. For example, the estimated data can be applied to determine responsibility after an intersection accident. In addition, in terms of preventing traffic accidents, the estimated results can be used in the learning algorithm for the prediction of related vehicle collision accidents to predict and warn about upcoming accidents. With the development of networked vehicle technology and the gradual improvement of infrastructure, vehicle collision accident prediction and early warning information can be transmitted to vehicles through the vehicle-road communication network, so that drivers or assisted driving syste...

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
IPC IPC(8): G06F17/50G06T7/277G06T7/70
CPCG06T7/277G06T7/70G06T2207/10016G06T2207/30236G06T2207/30241Y02T90/00
Inventor 杨腾飞巨志扬张辉
Owner 上海智驾汽车科技有限公司