Method for selecting an image detail of a sensor

Patent metadata

Field	Value
Publication number	US-11989944-B2
Application number	US-201917272638-A
Country	US
Kind code	B2
Filing date	Sep 4, 2019
Priority date	Sep 6, 2018
Publication date	May 21, 2024
Grant date	May 21, 2024

Abstract

A method for selecting a detail for a surroundings detection by a sensor based on sensor data. The surroundings are detected by at least one additional sensor, and an object recognition is carried out based on the ascertained sensor data of the at least one additional sensor. Pieces of position information from at least one recognized object are transformed into a coordinate system of the sensor, based on the object recognition, and based on the transformed pieces of position information, the sensor uses a detail of a scanning area for the surroundings detection, or an image detail from already detected sensor data, for an evaluation. A control device is also described.

First claim

What is claimed is:

1. A method for selecting a detail for a surroundings detection by a sensor based on sensor data, the method comprising:
detecting surroundings by at least one additional sensor to provide ascertained sensor data;
carrying out an object recognition based on the ascertained sensor data of the at least one additional sensor;
transforming pieces of position information of at least one recognized object into a coordinate system of the sensor; and
using, based on the object recognition, and based on the transformed pieces of position information, for an evaluation, by the sensor an image detail from already detected sensor data of the sensor;
wherein the pieces of position information include object dimensions and an object position in the sensor or the coordinate system, wherein data transmission between the sensors includes the pieces of information, wherein based on a relative arrangement of the sensors, the pieces of position information are used to compute the image detail in which the sensor detects the object ascertained by the additional sensor.

2. The method as recited in claim 1 , wherein the sensor uses at least one image detail from the already detected sensor data for the evaluation, based on transformed pieces of position information from multiple additional sensors.

3. The method as recited in claim 1 , wherein the transformation of the pieces of position information is carried out by a central control unit or by a sensor control unit.

4. The method as recited in claim 1 , wherein the transformation of the pieces of position information is carried out by the additional sensor, direct communication links being established between the sensor and the additional sensor.

5. The method as recited in claim 1 , wherein the pieces of position information of the at least one object, provided by the at least one sensor, are changed over time for tracking the at least one object.

6. The method as recited in claim 5 , wherein a temporally variable adaptation of the pieces of position information of the at least one object is continued outside a scanning area of the at least one additional sensor.

7. The method as recited in claim 1 , wherein the at least one image detail of the detected sensor data of the sensor that is used for the evaluation is selected based on additional sensor data of a position sensor and data of a map.

8. The method as recited in claim 1 , wherein the at least one image detail of the detected sensor data of the sensor that is used for the evaluation is selected based on position data of at least one road user, the position data of the at least one road user being transmitted via a direct or indirect communication link.

9. The method as recited in claim 1 , wherein the at least one image detail of the detected sensor data of the sensor is selected by an artificial intelligence.

10. The method as recited in claim 1 , wherein the evaluation carried out by the sensor is used for a plausibility check of the object recognition of the at least one additional sensor.

11. The method as recited in claim 10 , wherein the plausibility check is carried out via a request from at least one sensor.

12. The method as recited in claim 1 , wherein selection of the object from the image data of the sensor takes place by analyzing only the relevant image detail from a sensor scan.

13. A control unit to connect to at least one sensor and to read out sensor data from the at least one sensor, comprising:
a control unit configured to select a detail for a surroundings detection by a sensor based on sensor data, and configured to perform the following:
detecting surroundings using at least one additional sensor to provide ascertained sensor data;
carrying out an object recognition based on the ascertained sensor data of the at least one additional sensor;
transforming pieces of position information of at least one recognized object into a coordinate system of the sensor; and
using, based on the object recognition, and based on the transformed pieces of position information, for an evaluation an image detail from already detected sensor data of the sensor;
wherein the pieces of position information include object dimensions and an object position in the sensor or the coordinate system, wherein data transmission between the sensors includes the pieces of information, wherein based on a relative arrangement of the sensors, the pieces of position information are used to compute the image detail in which the sensor detects the object ascertained by the additional sensor.

14. The control unit as recited in claim 13 , wherein selection of the object from the image data of the sensor takes place by analyzing only the relevant image detail from a sensor scan.

Assignees

• Bosch Gmbh Robert

Inventors

• Ewert Marlon Ramon

Classifications

• G06V20/56 Primary

  exterior to a vehicle by using sensors mounted on the vehicle · CPC title

• G01S7/4811

  common to transmitter and receiver · CPC title

• G01S7/4817

  relating to scanning · CPC title

• G01S17/931

  of land vehicles · CPC title

• G06V10/811

  the classifiers operating on different input data, e.g. multi-modal recognition · CPC title