Method for detecting objects on a parking area

• US 10,007,268 B2
• Filed: 08/25/2016
• Issued: 06/26/2018
• Est. Priority Date: 09/03/2015
• Status: Active Grant

• Current Assignee: Robert Bosch GmbH
• Original Assignee: Robert Bosch GmbH
• Inventors: Rexilius, Jan, Nordbruch, Stefan
• Primary Examiner(s): Mehta, Bhavesh
• Assistant Examiner(s): Lemieux, Ian
• Application Number:
  US15/247,278
• Publication Number:
  US 20170069093A1
• Time in Patent Office: 670 Days
• CPC Class Codes: G05D 1/0246 using a video camera in combination with image processing means
• CPC Class Codes: G05D 1/0276 using signals provided by a source external to the vehicle involving a plurality of vehicles G05D1/0287; automatically controlling vehicle speed responsive to externally generated signals B60K31/0058
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/30241 Trajectory
• CPC Class Codes: G06T 2207/30261 Obstacle
• CPC Class Codes: G06T 2207/30264 Parking
• CPC Class Codes: G06T 7/20 Analysis of motion motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51
• CPC Class Codes: G06T 7/337 involving reference images or patches
• CPC Class Codes: G06V 20/52 Surveillance or monitoring of activities, e.g. for recognising suspicious objects recognising microscopic objects G06V20/69
• CPC Class Codes: G06V 20/58 Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
• CPC Class Codes: G08G 1/04 using optical or ultrasonic detectors
• CPC Class Codes: G08G 1/048 with provision for compensation of environmental or other condition, e.g. snow, vehicle stopped at detector
• CPC Class Codes: H04N 23/90 Arrangement of cameras or camera modules, e.g. multiple cameras in TV studios or sports stadiums

Abstract

A method for detecting objects on a parking area for vehicles with the aid of image processing of images from at least two imaging sensors, detection ranges of the imaging sensors overlapping at least partially. The images of an imaging sensor whose image quality is limited by environmental conditions are weighted less strongly for the detection of objects on the parking area during image processing than images of an imaging sensor whose image quality is not limited by environmental conditions. A processing unit, a program, and an overall system for carrying out the method are also described.

Claims

1. A method for detecting objects on a parking area for vehicles with the aid of image processing of images from at least two imaging sensors, wherein detection ranges of the imaging sensors overlap at least partially, the method comprising:

determining which of the imaging sensors has an image quality limited by environmental conditions, the determining being based on;

(i) a position and orientation of each of the imaging sensors, (ii) a date, and (iii) a time;

processing images from the imaging sensors including less strongly weighting images of the determined imaging sensor of the imaging sensors whose image quality is limited by environmental conditions than images of an imaging sensor of the imaging sensors whose image quality is not limited by environmental conditions; and

detecting objects on the parking area based on the processed images.

2. The method as recited in claim 1, wherein the imaging sensors are each designed as at least one of a camera, a laser scanner, a radar scanner, and a LIDAR scanner.

3. The method as recited in claim 1, wherein objects on the parking area are detected with the aid of image processing of images from more than two imaging sensors, detection ranges of more than two imaging sensors in each case overlapping at least partially.

4. The method as recited in claim 1, wherein the limited image quality of an imaging sensor is detected with the aid of image processing.

5. The method as recited in claim 4, wherein the limited image quality of an imaging sensor is ascertained with the aid of a comparison of an image from the imaging sensor to a reference image of the imaging sensor recorded at another point in time.

6. The method as recited in claim 1, wherein a piece of information about an object detected on the parking area, including a position and a dimension of the detected object, is relayed with the aid of a transmitter to a receiver in a vehicle including a device for automatically executing at least one driving function.

7. The method as recited in claim 1, wherein a trajectory for a vehicle including a device for automatically executing at least one driving function is calculated based on the objects detected on the parking area, and the trajectory is relayed with the aid of a transmitter to a receiver in the vehicle.

8. A processing unit, which includes connections for at least two imaging sensors, for detecting objects on a parking area for vehicles with the aid of image processing of images from the imaging sensors, wherein detection ranges of the imaging sensors overlap at least partially, the processing unit designed to:

determine which of the imaging sensors has an image quality limited by environmental conditions, the determining being based on;

(i) a position and orientation of each of the imaging sensors, (ii) a date, and (iii) a time;

process images from the imaging sensors including less strongly weighting images of the determined imaging sensor of the imaging sensors whose image quality is limited by environmental conditions than images of an imaging sensor of the imaging sensors whose image quality is not limited by environmental conditions; and

detect objects on the parking area based on the processed images.

9. The processing unit as recited in claim 8, wherein the processing unit further comprises a transmitter.

10. A non-transitory computer-readable storage medium storing program code for detecting objects on a parking area for vehicles with the aid of image processing of images from at least two imaging sensors, the program code, when executed by a processing unit, causing the processing unit to perform:

determining which of the imaging sensors has an image quality limited by environmental conditions, the determining being based on;

(i) a position and orientation of each of the imaging sensors, (ii) a date, and (iii) a time;

processing images from the imaging sensors including less strongly weighting images of the determined imaging sensor of the imaging sensors whose image quality is limited by environmental conditions than images of an imaging sensor of the imaging sensors whose image quality is not limited by environmental conditions; and

detecting objects on the parking area based on the processed images.

11. An overall system, comprising:

at least two imaging sensors; and

a processing unit including a transmitter, the processing unit connected to the imaging sensors;

wherein the overall system is configured to determine which of the imaging sensors has an image quality limited by environmental conditions, the determining being based on;

(i) a position and orientation of each of the imaging sensors, (ii) a date, and (iii) a time, process images from the imaging sensors including less strongly weighting images of the determined imaging sensor of the imaging sensors whose image quality is limited by environmental conditions than images of an imaging sensor of the imaging sensors whose image quality is not limited by environmental conditions, and detect objects on the parking area based on the processed images.