Passive camera based cloud detection and avoidance for aircraft systems

In an aircraft including a computerized aircraft navigation system, a method of detecting and avoiding cloud formations, the method comprising the steps of:

• acquiring with a camera, consecutively and in real time, a plurality of images within a field of view of the camera;
• providing said plurality of images to a central processing unit integrated with said camera,
• said central processing unit running a software application which is operative for
• receiving said plurality of images,
• detecting a plurality of feature points of cloud formations in each of said plurality of images,
• tracking said plurality of feature points across said plurality of images to create a plurality of 2-dimensional feature tracks,
• estimating 3-dimensional positions of said feature points in said 2-dimensional feature tracks to obtain estimated 3-dimensional feature tracks,
• generating macro representations of cloud formations based on said 3-dimensional feature tracks,
• wherein said step of generating said macro representations includes clustering said 3-dimensional feature tracks into cloud clusters, and wherein said step of clustering includes
• determining within said images pixels belonging to cloud formations and pixels belonging to background,
• measuring a distance between selected pixels using a distance function in 3-dimensional space,
• adding a prohibitive distance to said measured distance if said pixels are on different cloud formations, and
• setting a predetermined distance threshold for clustering whereby pixels on different cloud formations are not clustered;
• and
• determining if said generated macro representations of said cloud formations are within a pre-determined distance threshold;
• comparing a future trajectory of said aircraft with said macro representations of said cloud formations to detect relative position,
• recalculating, if needed, said future trajectory to avoid said generated macro representations of said cloud formations, and
• communicating said recalculated future trajectory to an autonomous aircraft navigation unit integrated with said camera and said central processing unit;
• and
• causing said aircraft to be autonomously navigated based on said recalculated future trajectory.