Collision prediction

1. A method comprising:

determining, using detected features in a plurality of digital video frames and between at least a pair of the plurality of digital video frames, an inter-frame rate of expansion in an area characterized by at least one group of features;

determining, based on the detected features and between at least the pair of the plurality of digital video frames, an average of an inter-frame difference in pixel position of at least two features in the at least one group of features;

calculating a likelihood of collision, wherein the likelihood of collision includes a ratio between the determined inter-frame rate of expansion and the determined average of inter-frame difference in pixel position;

comparing the likelihood of collision to a threshold; and

generating, in response to the likelihood of collision exceeding the threshold, an alarm that causes a vehicle to turn and/or causes the vehicle to slow down;

wherein at least one of the receiving, the detecting, the determining the inter-frame rate of expansion, the determining the average inter-frame difference in pixel position, the calculating, the comparing, and the generating is performed by at least one data processor.

2. The method of claim 1 , wherein the inter-frame rate of expansion characterizes a difference in an area defined by a convex hull of the at least one group of features.

3. The method of claim 1 , further comprising:

receiving data characterizing the plurality of digital video frames; and

detecting the plurality of features in the plurality of digital video frames.

4. The method of claim 1 , further comprising:

compensating, based on received data, the average inter-frame difference in pixel position, wherein the received data characterizes a motion of a camera, the motion being associated with the plurality of digital video frames.

5. The method of claim 1 , further comprising:

classifying the at least one group of features as being on a collision trajectory by at least comparing a collision point with a predetermined value defining a safety envelope around a camera.

6. A non-transitory computer readable storage medium comprising executable instructions which when executed by at least one processor provides operations comprising:

determining, using detected features in a plurality of digital video frames and between at least a pair of the plurality of digital video frames, an inter-frame rate of expansion in an area characterized by at least one group of features;

determining, based on the detected features and between at least the pair of the plurality of digital video frames, an average of an inter-frame difference in pixel position of at least two features in the at least one group of features;

calculating a likelihood of collision, wherein the likelihood of collision includes a ratio between the determined inter-frame rate of expansion and the determined average inter-frame difference in pixel position;

comparing the likelihood of collision to a threshold; and

generating, in response to the likelihood of collision exceeding the threshold, an alarm that causes a vehicle to turn and/or causes the vehicle to slow down.

7. The non-transitory computer readable storage medium of claim 6 , further comprising:

receiving data characterizing the plurality of digital video frames; and

detecting the plurality of features in the plurality of digital video frames.

8. The non-transitory computer readable storage medium of claim 6 , further comprising:

compensating, based on received data, the average inter-frame difference in pixel position, wherein the received data characterizes a motion of a camera, the motion being associated with the plurality of digital video frames.

9. The non-transitory computer readable storage medium of claim 6 , further comprising:

classifying the at least one group of features as being on a collision trajectory by at least comparing a collision point with a predetermined value defining a safety envelope around a camera.

10. A system comprising:

at least one processor circuitry;

at least one memory storing instructions which, when executed by the at least one processor circuitry, causes operations comprising:

determining, using detected features in a plurality of digital video frames and between at least a pair of the plurality of digital video frames, an inter-frame rate of expansion in an area characterized by at least one group of features;

determining, based on the detected features and between at least the pair of the plurality of digital video frames, an average of an inter-frame difference in pixel position of at least two features in the at least one group of features;

calculating a likelihood of collision, wherein the likelihood of collision includes a ratio between the determined inter-frame rate of expansion and the determined average inter-frame difference in pixel position;

comparing the likelihood of collision to a threshold; and

generating, in response to the likelihood of collision exceeding the threshold, an alarm that causes a vehicle to turn and/or causes the vehicle to slow down.

11. The system of claim 10 , wherein the inter-frame rate of expansion characterizes a difference in an area defined by a convex hull of the at least one group of features.

12. The system of claim 10 , wherein the operations further comprise:

receiving data characterizing the plurality of digital video frames; and

detecting the plurality of features in the plurality of digital video frames.

13. The system of claim 10 , wherein the operations further comprise:

compensating, based on received data, the average inter-frame difference in pixel position, wherein the received data characterizes a motion of a camera, the motion being associated with the plurality of digital video frames.

14. The system of claim 10 , wherein the operations further comprise:

classifying the at least one group of features as being on a collision trajectory by comparing a collision point with a predetermined value defining a safety envelope around a camera.