Method and device for fusion of measurements from different information sources

Patent metadata

Field	Value
Publication number	US-11521027-B2
Application number	US-201816770713-A
Country	US
Kind code	B2
Filing date	Dec 7, 2018
Priority date	Dec 20, 2017
Publication date	Dec 6, 2022
Grant date	Dec 6, 2022

Abstract

The invention relates to a method and a device for fusion of measurements from various information sources (I 1, I 2, . . . , I m) in conjunction with filtering of a filter vector, wherein the information sources (I 1, I 2, . . . , I m) comprise one or more environment detection sensor(s) of an ego vehicle,wherein in each case at least one measured quantity derived from the measurements is contained in the filter vector,wherein the measurements from at least one individual information source (I 1; I 2; . . . , I m) are mapped nonlinearly to the respective measured quantity, wherein at least one of these mapping operations depends on at least one indeterminate parameter,wherein the value to be determined of the at least one indeterminate parameter is estimated from the measurements of the different information sources (I 1, I 2, . . . , I m) andwherein the filter vector is not needed for estimating the at least one indeterminate parameter.

First claim

The invention claimed is:

1. A method for fusion of measurements from various information sources in conjunction with filtering of a filter vector indicating a distance from an ego vehicle to an object vehicle, wherein the information sources comprise one or more environment detection sensors of the ego vehicle, the method comprising:
determining a first distance from the ego vehicle to the object vehicle from the measurements of at least one of the various information sources;
determining a second distance from the ego vehicle to the object vehicle from the measurements of at least another one of the various information sources;
using the first distance and the second distance to produce the filter vector indicating changes in the first distance and second distance over time;
mapping the measurements from the information sources nonlinearly to the filter vector, wherein the mapping of the measurements depends on at least one indeterminate parameter that is based on a physical parameter of the object vehicle; and
estimating the at least one indeterminate parameter from a relationship between the measurements of the different information sources, wherein the estimation is performed independent of the filter vector.

2. The method according to claim 1 , wherein the method is used for tracking an object in the environment of the ego vehicle.

3. The method according to claim 2 , wherein the quantity derived from the measurements is the distance between the ego vehicle and an object vehicle, wherein a first information source consists in a first evaluation of an image from a vehicle camera of the ego vehicle supplying, by way of determination of the width of the object vehicle in the image from the vehicle camera, assuming a predetermined average width for vehicles as the corresponding width of the object vehicle, a first measured quantity for the distance between ego and object vehicles, wherein a first indeterminate parameter is the actual width of the object vehicle.

4. The method according to claim 3 , wherein a second information source consists in a second evaluation of the image from the vehicle camera of the ego vehicle supplying, by way of measurement of the vertical position of the vehicle lower edge of the object vehicle in the image from the vehicle camera, a second measured quantity for the distance between ego and object vehicles, wherein a second indeterminate parameter is the true height of the camera above the carriageway plane.

5. The method according to claim 1 , wherein the filtering of the filter vector is temporal filtering.

6. The method according to claim 5 , wherein the following steps are carried out in one time step of the filtering:
prediction of the filter vector,
updating of the filter vector by at least one new measurement, and
updating of the estimate of the at least one indeterminate parameter by the at least one new measurement.

7. The method according to claim 6 , wherein in the third step the filter vector is not used to update the estimate of the at least one indeterminate parameter.

8. The method according to claim 1 , wherein the measured quantities are derived using different measuring or evaluation methods of an environment detection sensor.

9. The method according to claim 1 , wherein the measured quantities are derived from measurements from different environment detection sensors or different environment detection sensor types as information sources.

10. The method according to claim 1 , wherein one of the measurements, which is determined by means of a reference measurement method, supplies a reference measured quantity, which is not dependent on a first unknown parameter, on which at least one measured quantity from another measurement is dependent.

11. The method according to claim 10 , wherein the reference measurement method is dependent on a second independent parameter, wherein a parameter value is predetermined for the second independent parameter.

12. A device, which is configured for fusion of measurements from different information sources in conjunction with filtering of a filter vector indicating a distance from an ego vehicle to an object vehicle, wherein the information sources comprise one or more environment detection sensors of the ego vehicle, the device comprising:
a processor configured to:
determine a first distance from the ego vehicle to the object vehicle from the measurements of at least one of the various information sources in relation to the information to be determined,
determine a second distance from the ego vehicle to the object vehicle from the measurements of at least another one of the various information sources,
use the first distance and the second distance to produce the filter vector indicating changes in the first distance and second distance over time,
map the measurements from the information sources nonlinearly to the filter vector, wherein the map of measurements depends on at least one indeterminate parameter that is based on a physical parameter of the object vehicle, and
estimate the at least one indeterminate parameter from a relationship between the measurements of the different information sources, wherein the estimation is performed independent of the filter vector.

Assignees

• Conti Temic Microelectronic Gmbh

Inventors

• Stueck Robert

Classifications

• G06T7/277 Primary

  involving stochastic approaches, e.g. using Kalman filters · CPC title

• G06V20/584

  of vehicle lights or traffic lights · CPC title

• G06V10/803

  of input or preprocessed data · CPC title

• G06F18/251

  of input or preprocessed data · CPC title

• G06V20/58

  Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads · CPC title