Hazard detection from a camera in a scene with moving shadows

A computerized method for processing images captured by a camera mountable in a host vehicle while the host vehicle is moving, the method comprising:

• capturing a first image frame and a second image frame from a field of view of the camera;
• tracking corresponding image points from the first image frame to the second image frame;
• detecting, from the tracked corresponding image points and based on a comparison of the first image frame to the second image frame, a first plurality of image points associated with a suspect hazard of a road;
• detecting, from the tracked corresponding image points, a second plurality of image points associated with a moving vehicle;
• determining first motion between the first plurality of image points and second motion between the second plurality of image points;
• and
• determining that the first motion is associated with a moving shadow cast from the moving vehicle based on a correlation between the first motion and the second motion.

A system for a host vehicle, the system comprising:

• a memory storing instructions;
• and
• a processor configured to execute the instructions to cause the processor to:
• capture a first image frame and a second image frame from a field of view of the camera;
• track corresponding image points from the first image frame to the second image frame;
• detect, from the tracked corresponding image points and based on a comparison of the first image frame to the second image frame, a first plurality of image points associated with a suspect hazard of a road;
• detect, from the tracked corresponding image points, a second plurality of image points associated with a moving vehicle;
• determine first motion between the first plurality of image points and second motion between the second plurality of image points;
• and
• determine that the first motion is associated with a moving shadow cast from the moving vehicle based on a correlation between the first motion and the second motion.

A non-transitory computer readable medium containing instructions that, when executed by at least one processor, cause the at least one processor to perform operations comprising:

• capturing a first image frame and a second image frame from a field of view of the camera;
• tracking corresponding image points from the first image frame to the second image frame;
• detecting, from the tracked corresponding image points and based on a comparison of the first image frame to the second image frame, a first plurality of image points associated with a suspect hazard of a road;
• detecting, from the tracked corresponding image points, a second plurality of image points associated with a moving vehicle;
• determining first motion between the first plurality of image points and second motion between the second plurality of image points;
• and