Fusion of far infrared and visible images in enhanced obstacle detection in automotive applications

摘要

A computerized system mountable on a vehicle operable to detect an object by processing first image frames from a first camera and second image frames from a second camera. A first range is determined to said detected object using the first image frames. An image location is projected of the detected object in the first image frames onto an image location in the second image frames. A second range is determined to the detected object based on both the first and second image frames. The detected object is tracked in both the first and second image frames When the detected object leaves a field of view of the first camera, a third range is determined responsive to the second range and the second image frames.

主权项

1. A method performable by a computerized system mountable on a vehicle, wherein the system includes a first camera and a second camera connectible to a processor, the method comprising:
first capturing a plurality of first image frames from the first camera; second capturing a plurality of second image frames from the second camera; detecting said object by processing said first image frames thereby producing a detected object; first determining a first range to said detected object using said first image frames; projecting an image location of said detected object in at least one of said first image frames onto an image location in at least one of said second image frames; second determining a second range from the vehicle to said detected object based on both said first image frames and said second image frames; and tracking said detected object in both said first image frames and second image frames and when said detected object leaves a field of view of the first camera, third determining a third range to said detected object responsive to said second range and said second image frames.