Augmented object detection using structured light

• US 10,181,085 B2
• Filed: 11/05/2015
• Issued: 01/15/2019
• Est. Priority Date: 11/05/2014
• Status: Active Grant

• Current Assignee: TRW Automotive USLLC (Zeppelin - Stiftung der Stadt Friedrichshafen)
• Original Assignee: TRW Automotive USLLC (Zeppelin - Stiftung der Stadt Friedrichshafen)
• Inventors: Schamp, Gregory G.
• Primary Examiner(s): Gilliard, Delomia L
• Application Number:
  US15/518,866
• Publication Number:
  US 20170236014A1
• Time in Patent Office: 1,167 Days
• Field of Search: None
• CPC Class Codes: B60R 1/002 specially adapted for covering the peripheral part of the vehicle, e.g. for viewing tyres, bumpers or the like integrated in the windows B60R1/001; combined with rear-view mirrors B60R1/08
• CPC Class Codes: B60R 2300/202 displaying a blind spot scene on the vehicle part responsible for the blind spot
• CPC Class Codes: B60R 2300/802 for monitoring and displaying vehicle exterior blind spot views
• CPC Class Codes: G01B 11/026 by measuring distance between sensor and object G01B11/0608 takes precedence
• CPC Class Codes: G01B 11/14 for measuring distance or clearance between spaced objects or spaced apertures G01B11/26 takes precedence; rangefinders G01C3/00
• CPC Class Codes: G01C 11/025 by scanning the object
• CPC Class Codes: G01S 17/46 Indirect determination of position data
• CPC Class Codes: G01S 17/931 of land vehicles
• CPC Class Codes: G01V 8/10 Detecting, e.g. by using light barriers by reflection from the object G01S17/00
• CPC Class Codes: G06T 7/11 Region-based segmentation
• 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: H04N 23/56 provided with illuminating means
• CPC Class Codes: H04N 7/183 for receiving images from a single remote source

Abstract

Systems and methods are provided for imaging a region of interest. A structured light source is configured to provide a substantially two-dimensional light curtain within a field of view of the camera formed by at least one projected laser beam at a wavelength detectable by the camera. An image analysis component is configured to detect objects within the region of interest from at least a position of the at least one projected laser beam within the image.

Claims

1. An object detection system for detecting objects within a region of interest, comprising:

a camera configured to image a region of interest to provide an image;

a structured light source configured to provide a first two-dimensional light curtain and a second two-dimensional light curtain that is perpendicular to the first two-dimensional light curtain within a field of view of the camera, such that point of intersection of the first two-dimensional light curtain and the second two-dimensional light curtain represents a known reference point within the image, each of the first two-dimensional light curtain and a second two-dimensional light curtain being formed by at least one projected laser beam at a wavelength detectable by the camera; and

an image analysis component configured to detect objects within the region of interest from at least a position of the first two-dimensional light curtain within the image using the position of the point of intersection within the image as the known reference point to transform the position of the first two-dimensional light curtain in the image to a real world coordinate domain.

2. The object detection system of claim 1, wherein the structured light source comprises a laser diode and a beam shaping optical component configured to produce the two-dimensional light curtain.

3. The object detection system of claim 2, the laser diode being configured as to produce light within the infrared band.

4. The object detection system of claim 1, wherein the camera is mounted to a vehicle at a first location and the structured light source is mounted to the vehicle at a second location, spatially remote from the first location.

5. The object detection system of claim 1, wherein the image analysis system is configured to evaluate an intersection of the two-dimensional light curtain with the ground within the image, with the presence of an object being indicated by a deviation of a line formed by the intersection from an expected baseline.

6. The object detection system of claim 1, the structured light source being further configured to provide a third two-dimensional light curtain within the field of view of the camera, the third two-dimensional light curtain being parallel to the first two-dimensional light curtain.

7. The object detection system of claim 6, wherein the image analysis component is configured to evaluate respective intersections of each of the first two-dimensional light curtain and the third two-dimensional light curtain with the ground within the image, with the presence of an object at a first distance being indicated by a deviation of a line formed by the intersection of the first two-dimensional light curtain and the ground from a first expected baseline and the presence of an object at a second distance being indicated by a deviation of a line formed by the intersection of the third two-dimensional light curtain and the ground from a second expected baseline.

8. The object detection system of claim 1, wherein the structured light source is configured to have a dispersion angle between forty degrees and fifty degrees.

9. The object detection system of claim 1, the image analysis component comprising a coordinate transform component configured to apply a coordinate transform to the image, such that for each pixel (x, y) within the image, where x represents a column in which the pixel is located and y is a row in which the pixel is located, a position (X, Z), where X represents a distance cross range of the camera and Z represents a distance downrange of the camera, is determined as

10. The object detection system of claim 1, the object detection system comprising an elevation calculation component configured to determine an elevation, Y, at a given location from its distance, Z, downrange of the camera and a row, y, in which the pixel representing the location is located as

11. A method for detecting objects within a region of interest, comprising:

projecting a first two-dimensional light curtain into a region of interest;

projecting a second two-dimensional light curtain into the field of view of the camera that is perpendicular to the first two-dimensional light curtain such that point of intersection of the first two-dimensional light curtain and the second two-dimensional light curtain represents a known reference point within the image;

imaging the region of interest at a camera to provide an image, such that an intersection of the at least one of the first two-dimensional light curtain and a second two-dimensional light curtain with the ground is visible; and

determining that an object is present from a deviation of an intersection of the two-dimensional light curtain with the ground from an expected baseline and a position of the point of intersection within the image.

12. The method of claim 11, further comprising projecting a third two-dimensional light curtain into the region of interest, with the third two-dimensional light curtain being parallel to the first two-dimensional light curtain.

13. The method of claim 12, wherein determining that the object is present comprising determining the presence of the object at a first distance if a line formed by the intersection of the first two-dimensional light curtain and the ground deviates from a first expected baseline and determining the presence of an object at a second distance if a line formed by the intersection of the third two-dimensional light curtain and the ground deviates from a second expected baseline.

14. The method of claim 11, further comprising applying a coordinate transform to the image, such that for each pixel (x, y) within the image, where x represents a column in which the pixel is located and y is a row in which the pixel is located, a position (X, Z), where X represents a distance cross range of the camera and Z represents a distance downrange of the camera, is determined as

15. The method of claim 14, further comprising determining an elevation, Y, at a given location from its distance, Z, downrange of the camera and a row, y, in which the pixel representing the location is located as

16. An object detection system for detecting objects within one of a blind spot and a region rearward of a vehicle, comprising:

a camera configured to image the one of the blind spot and the region rearward of the vehicle;

a structured light source, comprising a laser diode and a beam shaping optical component, configured to provide a first two-dimensional light curtain and a second two-dimensional light curtain that is perpendicular to the first two-dimensional light curtain within a field of view of the camera, such that point of intersection of the first two-dimensional light curtain and the second two-dimensional light curtain represents a known reference point within the image, each of the first two-dimensional light curtain and a second two-dimensional light curtain being formed by at least one projected laser beam at a wavelength detectable by the camera; and

an image analysis component configured to detect objects within the one of the blind spot and the region rearward of the vehicle from at least a position of the at least one projected laser beam within the image and a position of the point of intersection within the image by applying a coordinate transform to the image, such that for each pixel (x, y) within the image, where x represents a column in which the pixel is located and y is a row in which the pixel is located, the position where X represents a distance cross range of the camera and Z represents a distance downrange of the camera, is determined as

17. The object detection system of claim 16, wherein the camera is mounted to a vehicle at a first location and the structured light source is mounted to the vehicle at a second location, spatially remote from the first location.

18. The object detection system of claim 16, wherein the image analysis system is configured to evaluate an intersection of the two-dimensional light curtain with the ground within the image, with the presence of an object being indicated by a deviation of a line formed by the intersection from an expected baseline.