Automated vehicle object detection system with camera image and radar data fusion

Patent metadata

Field	Value
Publication number	US-10037472-B1
Application number	US-201715465296-A
Country	US
Kind code	B1
Filing date	Mar 21, 2017
Priority date	Mar 21, 2017
Publication date	Jul 31, 2018
Grant date	Jul 31, 2018

Abstract

An object detection system for an automated vehicle includes a radar, a camera, and a controller. The radar detects a cluster of targets characterized by a radar-distance (x) from the host-vehicle. The camera renders an image of an object and a lane-marking present in the area. The controller is configured to determine an equation that is a function of a longitudinal-distance from the host-vehicle and corresponds to the lane-marking, determine a first-optical-angle (θ) based on a first-image-distance between a reference-point on the object and a spot on the image indicated by the equation where the longitudinal-distance is equal to the radar-distance, determine a lateral-distance (Dist_LM) between the object and the lane-marking based on the first-optical-angle and the radar-distance, and determine a first-lateral-offset (y RM ) between the object and a longitudinal-axis of the host-vehicle based on the lateral-distance and a first-value of the equation where the longitudinal-distance is equal to the radar-distance.

First claim

We claim:

1. An object detection system for an automated vehicle, said system comprising:
a radar that detects targets in an area proximate to a host-vehicle, wherein a cluster of targets is characterized by a radar-distance (x) from the host-vehicle;
a camera that renders an image of an object and a lane-marking present in the area; and
a controller in communication with the radar and the camera, said controller configured to determine an equation that is a function of a longitudinal-distance from the host-vehicle and corresponds to the lane-marking in the image,
determine a first-optical-angle (θ) based on a first-image-distance on the image between a reference-point on the object and a spot on the image indicated by a first-value of the equation where the longitudinal-distance is equal to the radar-distance,
determine a lateral-distance (Dist_LM) between the object and the lane-marking based on the first-optical-angle and the radar-distance,
determine a first-lateral-offset (yRM) between the object and a longitudinal-axis of the host-vehicle based on the lateral-distance and the first value, and
operate the host-vehicle in accordance with the lateral-distance and the first-lateral-offset.

2. The system in accordance with claim 1 , wherein the controller is further configured to determine the first-lateral-offset based on a second-value of the equation at the host-vehicle where the longitudinal-distance is equal to zero.

3. The system in accordance with claim 1 , wherein the system is further configured to operate the host-vehicle based on the first-lateral-offset.

4. The system in accordance with claim 1 , wherein the controller is further configured to
determine a second-optical-angle (a) based on a second-image-distance on the image between the reference-point on the object and a centerline of the image, wherein the centerline is selected to correspond to the longitudinal-axis, and
determine a second-lateral-offset (y*) between the object and the longitudinal-axis based on the second-optical-angle and the radar-distance.

5. The system in accordance with claim 4 , wherein the system is further configured to operate the host-vehicle based on the first-lateral-offset and the second-lateral-offset.

6. The system in accordance with claim 4 , wherein the controller is further configured to determine a match-probability based on an offset-difference between the first-lateral-offset and the second-lateral-offset.

7. The system in accordance with claim 6 , wherein the match-probability is further determined based on a range-difference between the radar-distance and an optical-distance indicated by a height of the object in the image.

8. The system in accordance with claim 7 , wherein the match-probability is further determined based on a rate-difference between a range-rate of the object indicated by the radar and an optical-rate indicated by a change-in-height of the object between the image and a prior-image.

Assignees

• Delphi Tech Inc

Inventors

• Chen Susan
• Schwartz David A
• Mangalgiri Anuradha
• Liu Yu
• Siegemund Jan

Classifications

• G06V20/58

  Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads · CPC title

• G01S13/42 Primary

  Simultaneous measurement of distance and other co-ordinates (indirect measurement G01S13/46) · CPC title

• G06F18/25

  Fusion techniques · CPC title

• G01S13/726

  Multiple target tracking · CPC title

• G01S13/867 Primary

  Combination of radar systems with cameras · CPC title