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

A method performable by a computerized system mounted to travel with a vehicle, the system comprising a first camera having a first field of view and a second camera having a second field of view, the method comprising:

• acquiring multiple first image frames via the first camera,
• acquiring multiple second image frames via the second camera,
• processing the first image frames to detect an object,
• processing the first image frames to determine a first distance between the vehicle and the detected object,
• projecting an image location of the detected object in at least one of the first image frames onto a location in at least one of the second image frames,
• processing the first image frames and the second image frames to determine a second distance between the vehicle and the detected object,
• tracking the detected object in the first image frames and the second image frames, and
• processing the second image frames and the second distance to determine a third distance between the vehicle and the detected object,
• whereby estimated distances between the vehicle and the detected object are provided when the detected object is inside the first field of view and when the detected object is outside the first field of view.

A computerized system mountable on a vehicle, the system comprising:

• a first camera and a second camera connectible to a processor,
• the processor operable to:
• acquire multiple first image frames from the first camera,
• acquire multiple second image frames from the second camera,
• detect an object by processing the first image frames to produce thereby a detected object,
• determine a first distance to the detected object using the first image frames,
• project an image location of the detected object in at least one of the first image frames onto an image location in at least one of the second image frames,
• determine a second distance from the vehicle to the detected object based on both the first image frames and the second image frames,
• track the detected object in both the first image frames and second image frames and when the detected object leaves a field of view of the first camera,
• determine a third distance to the detected object responsive to the second distance and the second image frames.