Automated Vehicle Object Detection Using Lane Marking Mediator
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Automated vehicle systems face errors in determining the lateral displacement of an object relative to its longitudinal axis, especially when navigating curved roadways, due to inaccuracies in matching vision and radar sensor measurements.
Innovation Solution
An object detection system that combines radar and camera data, using a controller to determine a lane-marking equation, optical angles, and lateral distances to accurately calculate the lateral offset of an object from the vehicle's longitudinal axis, incorporating vision-sensed lane-markings to improve matching accuracy and reduce scale errors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If radar and camera data are matched to determine lateral displacement, then object tracking capability is improved, but measurement accuracy deteriorates on curved roadways due to scale errors
Solution Approach 1:
The patent introduces lane markings as an intermediary reference element to mediate between radar distance measurements and camera image coordinates. By using the lane marking equation as a mediator, the system can accurately map radar-detected object positions to the curved roadway geometry, eliminating scale errors that occur when directly matching radar and camera data on curved roads.
Solution Approach 2:
The patent transforms the measurement parameters by introducing a lane marking equation that describes the curved roadway geometry. Instead of using fixed coordinate transformations, the system dynamically adjusts the spatial reference frame based on the lane marking curvature, changing the parameters used to calculate lateral displacement to account for roadway geometry.
2Device complexity
If direct radar-to-camera coordinate mapping is used, then system complexity is reduced, but measurement accuracy deteriorates due to roadway curvature
Solution Approach 1:
The lane marking serves as an intermediary that simplifies the coordinate mapping process. Rather than implementing complex direct transformation algorithms between radar and camera coordinates, the system uses the lane marking equation as an intermediate reference, making the mapping process more straightforward while improving accuracy on curved roadways.
Solution Approach 2:
The lane marking detection and equation generation is performed automatically by the camera system itself, providing self-service functionality. The system uses the camera's own image data to generate the lane marking equation, which then serves as the reference for coordinating radar measurements, eliminating the need for external reference systems or complex pre-programmed roadway models.
Data Source
AI summary
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 (yRM) 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.