Method for detecting objects

Patent metadata

Field	Value
Publication number	US-8982669-B2
Application number	US-201013510779-A
Country	US
Kind code	B2
Filing date	Nov 16, 2010
Priority date	Nov 23, 2009
Publication date	Mar 17, 2015
Grant date	Mar 17, 2015

Abstract

In a method for detecting objects, at least one sensor emits a transmitting pulse as a wave, particularly as an acoustic or an electromagnetic wave, which wave is reflected at least partially by objects in the propagation space, and the reflected wave being detected by at least one receiver as a received signal. The received signal of the reflected wave is divided up into segments, and from the individual segments, data are gathered that are drawn upon for the determination of an object hypothesis.

First claim

What is claimed is:

1. A method for detecting an object, comprising:
emitting, by at least one transmitter, a pulse as one of an acoustic wave or an electromagnetic wave, wherein said pulse is at least partially reflected by the object in the propagation space;
detecting, by at least one receiver, the reflected wave as a received signal;
dividing the received signal of the reflected wave into segments;
obtaining data from the segments of the received signal;
generating an object hypothesis from the data obtained from the segments of the received signal;
wherein the object hypothesis is generated using at least one of a model-based iterative approach, a support vector machine, and a Gaussian process.

2. The method as recited in claim 1 , wherein the received signal is divided into segments over time.

3. The method as recited in claim 2 , wherein a curve adjustment takes place for an envelope of the amplitude of the segments.

4. The method as recited in claim 2 , wherein data are ascertained on the decay behavior of the received signal.

5. The method as recited in claim 2 , wherein a pulse feature including at least one of a half-height width and an actual pulse height of the received signal is determined from the segments of the received signal.

6. The method as recited in claim 5 , wherein the object hypothesis includes information regarding at least one of a type of the object and a surface property of the object.

7. A method for detecting an object, comprising:
emitting, by at least one transmitter, a pulse as one of an acoustic wave or an electromagnetic wave, wherein said pulse is at least partially reflected by the object in the propagation space;
detecting, by at least one receiver, the reflected wave as a received signal;
dividing the received signal of the reflected wave into segments over time;
obtaining data from the segments of the received signal;
generating an object hypothesis from the data obtained from the segments of the received signal;
obtaining at least one of additional signals and digital map data by using a supplementary sensor system including at least one of a video scanner and a laser scanner; and
generating a three-dimensional environmental model using the at least one of additional signals and digital map data.

8. The method as recited in claim 7 , further comprising:
calculating a deviation of the object hypothesis from the three-dimensional environmental model.

9. The method as recited in claim 8 , wherein the transmitter includes at least one of:
at least one ultrasonic sensor which emits acoustic waves; and
at least one antenna which emits electromagnetic waves.

10. A device for detecting an object, comprising:
at least one transmitter emitting a pulse as one of an acoustic wave or an electromagnetic wave, wherein said pulse is at least partially reflected by the object in the propagation space;
at least one receiver detecting the reflected wave as a received signal;
means for dividing the received signal of the reflected wave into segments over time;
means for obtaining data from the segments of the received signal;
means for generating an object hypothesis from the data obtained from the segments of the received signal;
wherein the object hypothesis is generated using at least one of a model-based iterative approach, a support vector machine, and a Gaussian process.

11. The device as recited in claim 10 , wherein multiple transmitters are provided as a transmitter array for emitting multiple pulses at one of synchronized time intervals or at offset time intervals.

12. The method as recited in claim 1 , wherein the object hypothesis is generated using a model-based iterative approach.

13. The method as recited in claim 1 , wherein the object hypothesis is generated using a support vector machine.

14. The method as recited in claim 1 , wherein the object hypothesis is generated using a Gaussian process.

15. The device as recited in claim 10 , wherein the object hypothesis is generated using a model-based iterative approach.

16. The device as recited in claim 10 , wherein the object hypothesis is generated using a support vector machine.

17. The device as recited in claim 10 , wherein the object hypothesis is generated using a Gaussian process.

Assignees

• Barthel Paul
• Hagenmeyer Lorenz
• Mueller Martin
• Mielenz Holger
• Bosch Gmbh Robert

Inventors

• Barthel Paul
• Hagenmeyer Lorenz
• Mueller Martin
• Mielenz Holger

Classifications

• G01S7/412 Primary

  based on a comparison between measured values and known or stored values · CPC title

• G01S7/417

  involving the use of neural networks · CPC title

• G01S7/539

  using analysis of echo signal for target characterisation; Target signature; Target cross-section · CPC title

• G01S15/931

  of land vehicles · CPC title

• G01S15/86

  Combinations of sonar systems with lidar systems; Combinations of sonar systems with systems not using wave reflection · CPC title