Granted Patent B2

US 12,455,172 · App. 16/982,447 · Granted Oct 28, 2025

Inventors: Henning Hamer (Munich, DE); Holger Karn (Munich, DE)

Assignee: CONTINENTAL AUTOMOTIVE TECHNOLOGIES GMBH

G01C21/3815B60W60/001G01C21/3859

Abstract

Claims (60)

1. A system for generating, storing, and providing a digital road map, the system comprising:

a backend including a memory; and

an object recognition device including: a capture unit, an evaluation unit, a location sensor, and a transceiver in communication with the backend;

wherein the capture unit includes a camera and/or a sensor configured to capture surroundings data of a vehicle;

the location sensor comprises a global navigation satellite system or a cell positioning device configured to analyze the surroundings data to determine a position of the captured surroundings data and objects contained in the surroundings data;

the evaluation unit includes a processor programmed to recognize and identify the objects based on the surroundings data and to associate the objects with position information and to assess the surroundings data for concealed objects including objects stored in the digital road map but not recognizable in the surroundings data;

wherein the objects include one or more of: a guardrail, a road marking, traffic lights, a roundabout, a crosswalk, and a speed bump;

wherein the processor is further programmed to slice the digital road map into multiple sections based on a size of the section, wherein the size depends on both a geographical distance and a density of identified objects in the surroundings data;

the transceiver transmits information generated by the processor to the backend in separate packets, each packet containing one of the multiple sections;

the backend is configured to generate or to update the digital road map based on information from the transceiver;

each of the objects in the digital road map has an associated confidence value;

the backend increases the confidence value of a respective object if the respective object is contained in the received data;

the backend reduces the confidence value of the respective object if the respective object is not contained in the received data; and

the backend maintains the confidence value of any concealed object in the received data; and

the backend stores the digital road map including the objects along with the corresponding confidence value for each respective object.

2. The system as claimed in claim 1 , wherein:

the processor is further programmed to evaluate the surroundings data of a section of a route covered by the vehicle; and

the transceiver transmits the data of the section to the backend.

3. The system as claimed in claim 2 , wherein the section is 100 m long.

4. The system as claimed in claim 1 , wherein:

the processor is further programmed to initially classify all of the captured surrounding regions around the vehicle as concealed regions in the respective section and, if an object has been recognized in a surrounding region or if no concealment is recognized in the surrounding region, to classify the corresponding surrounding region as a visible region; and

the backend is configured not to incorporate the concealed surrounding regions into the determination of the confidence values of the individual objects in the digital road map.

5. The system as claimed in claim 1 , the object recognition device furthermore including a memory storing a digital road map containing a multiplicity of objects;

wherein the processor is further programmed to compare the recognized objects with the multiplicity of objects; and

the processor is further programmed to report recognized objects not present in the stored digital road map or unrecognized objects should have been recognized according to the digital road map to the backend.

6. The system as claimed in claim 1 , wherein the backend transmits the digital road map to a memory of the object recognition device at periodic time intervals.

7. The system as claimed in claim 6 , wherein the backend transmits only objects having a confidence value above a predefined threshold value to the memory.

8. The system as claimed in claim 1 , wherein the backend evaluates the received data and removes or integrates unrecognized objects or new objects into the digital road map based on the received data.

9. The system as claimed in claim 1 , wherein the data transmitted by the transceiver comprise vector data.

10. A vehicle comprising:

an object recognition device including: a capture unit, an evaluation unit, a location sensor, and a transceiver;

wherein the capture unit includes a camera and/or a sensor configured to capture surroundings data;

the location sensor comprises a global navigation satellite system or a cell positioning device configured to determine a position corresponding to the captured surroundings data and of any objects contained in the surroundings;

the evaluation unit includes a processor programmed to recognize and identify the objects based on the surroundings data and to associate the objects with position information and to assess the surroundings data for concealed objects including objects stored in the digital road map but not recognizable in the surroundings data;

wherein the identified objects include one or more of: a guardrail, a road marking, traffic lights, a roundabout, a crosswalk, and a speed bump;

wherein the processor is further programmed to slice the digital road map into multiple sections based on a size of the section, wherein the size depends on both a geographical distance and a density of identified objects in the surroundings data;

the transceiver transmits data generated by the processor to a backend in separate packets, each packet containing one of the multiple sections.

11. A backend storing a digital road map and confidence values for objects in the map;

wherein the backend slices the digital road map into multiple sections based on a size of the section, wherein the size depends on both a geographical distance and a density of identified objects in the surroundings data;

wherein the identified objects include one or more of: a guardrail, a road marking, traffic lights, a roundabout, a crosswalk, and a speed bump;

wherein the backend is programmed to receive data from a transceiver in separate packets, each packet containing one of the multiple sections and to generate or to update the digital road map;

wherein each object in the digital road map has an associated confidence value;

wherein the backend is programmed to increase the confidence value of a respective object if the respective object is represented in the received data; and

wherein the backend is programmed to lower the confidence value of the respective object if the respective object is not represented in the received data;

wherein the backend is programmed to maintain the confidence value of any concealed object in the received data; and

the backend stores the digital road map including the objects along with the corresponding confidence value for each respective object.

12. A method for maintaining a digital road map, the method comprising:

capturing surroundings data with a capture unit including a camera and/or a sensor;

determining a position of the captured surroundings data and any objects contained therein using a location sensor comprising a global navigation satellite system or a cell positioning device;

evaluating the captured surroundings data using a processor;

slicing the digital road map into multiple sections based on a size of the section, wherein the size depends on both a geographical distance and a density of objects in the surroundings data;

recognizing and identifying objects and concealed objects in the surroundings data based on the evaluation;

wherein the identified objects include one or more of: a guardrail, a road marking, traffic lights, a roundabout, a crosswalk, and a speed bump;

providing the identified objects and the concealed objects with position information from the location sensor;

transmitting the evaluated data using a transceiver to a backend in separate packets, each packet containing one of the multiple sections;

generating or updating the digital road map stored in the backend based on the received data;

increasing a confidence value of the respective object if the respective object is represented in the received data;

reducing the confidence value of the respective object if the respective object is not represented in the received data; and

maintaining the confidence value of any concealed object in the received data; and

the backend stores the digital road map including the objects along with the corresponding confidence value for each respective object.

Assignments (2)

Priority Claims (1)

Continuity (1)

References Cited (44)