Lane tracking system

摘要

A lane tracking system for tracking the position of a vehicle within a lane includes a camera configured to provide a video feed representative of a field of view and a video processor configured to receive the video feed from the camera and to generate latent video-based position data indicative of the position of the vehicle within the lane. The system further includes a vehicle motion sensor configured to generate vehicle motion data indicative of the motion of the vehicle, and a lane tracking processor. The lane tracking processor is configured to receive the video-based position data, updated at a first frequency; receive the sensed vehicle motion data, updated at a second frequency; estimate the position of the vehicle within the lane from the sensed vehicle motion data; and fuse the video-based position data with the estimate of the vehicle position within the lane using a Kalman filter.

主权项

1. A lane tracking system for tracking the position of a vehicle within a lane, the system comprising:
a camera configured to provide a video feed representative of a field of view; a video processor configured to receive the video feed and generate latent video-based position data, the video-based position data indicative of the position of the vehicle within the lane; a vehicle motion sensor configured to generate vehicle motion data indicative of the motion of a vehicle, wherein the generated latent video-based position data has a greater latency than the generated vehicle motion data; and a lane tracking processor configured to maintain a real-time position of the vehicle within the lane using the vehicle motion data and the latent video-based position data, and wherein maintaining the real-time position includes:
receiving the video-based position data, updated at a first frequency;receiving the sensed vehicle motion data, updated at a second frequency that is faster than the first frequency;estimating the real-time position of the vehicle within the lane from the sensed vehicle motion data;rolling back the real-time position estimate by a predefined number of increments upon receipt of the latent video-based position data;fusing the latent video-based position data with the rolled-back estimate of the vehicle position within the lane using Kalman filtering techniques to generate an updated latent vehicle position; andrecomputing the real-time position estimate using previously received vehicle motion data and the updated latent vehicle position.