Image processing to derive movement characteristics for a plurality of queue objects

1. A computer-implemented method for deriving movement characteristics for a plurality of queue objects that move inside a surveillance area to a target; the method comprising:

receiving a sequence of image frames that represent the surveillance area;

calculating flow vectors that indicate an optical displacement for the sequence of image frames;

extending one of the flow vectors as a lead vector in a first extension direction and in a second extension direction;

determining a first intermediate vector and a second intermediate vector by using flow vectors along the first extension and by using flow vectors along the second extension;

selecting one the intermediate vectors as the new lead vector;

repeating extending, determining and selecting to concatenate the lead vectors to the movement characteristics.

2. The method of claim 1 , wherein extending the lead vector is initialized by a flow vector that corresponds to location coordinates in the surveillance area near the target.

3. The method of claim 2 , wherein extending the lead vector is performed for directions that go away from the target.

4. The method according to claim 1 , wherein the first intermediate vector and the second intermediate vector are calculated by interpolation.

5. The method according to claim 4 , wherein the interpolation is a bilinear interpolation.

6. The method according to claim 1 , wherein selecting one the intermediate vectors as lead vector is performed for the intermediate vector that represents the larger displacement of the intermediate vectors.

7. The method according to claim 1 , wherein the image frames in the sequence of frames have data coordinates that are pixels.

8. The method according to claim 1 , wherein the movement characteristics includes a movement time (TM) in correspondence to the number of lead vectors.

9. The method according to claim 8 , wherein the movement time (TM) is related to location coordinates of the queue object and of the target.

10. The method according to claim 1 , wherein the characteristics include a queue length.

11. The method according to claim 1 , wherein the characteristics includes the identification of a queue tail as a location in that the flow vectors following the movement characteristics go below a threshold value.

12. A non-transitory program storage device readable by machine, tangibly embodying a program of instructions executable by the machine that performs the steps of a computer-implemented method for deriving movement characteristics for a plurality of queue objects that move inside a surveillance area to a target, the method being implemented by a processor to perform steps comprising:

receiving a sequence of image frames that represent the surveillance area;

calculating flow vectors that indicate an optical displacement for the sequence of image frames;

extending one of the flow vectors as a lead vector in a first extension direction and in a second extension direction;

determining a first intermediate vector and a second intermediate vector by using flow vectors along the first extension and by using flow vectors along the second extension;

selecting one the intermediate vectors as the new lead vector;

repeating extending, determining and selecting to concatenate the lead vectors to the movement characteristics.

13. A computer for deriving movement characteristics for a plurality of queue objects that move inside a surveillance area to a target; the computer comprising:

a memory; and

a processor, coupled to the memory, configured to:

receive a sequence of image frames that represent the surveillance area and to calculate flow vectors that indicate an optical displacement for the sequence of image frames; and

extend one of the flow vectors as a lead vector in a first extension direction and in a second extension direction, to determine a first intermediate vector and a second intermediate vector by using flow vectors along the first extension direction and by using flow vectors along the second extension direction, to select one the intermediate vectors as a new lead vector, and to concatenate lead vectors to the movement characteristics.

14. The computer of claim 13 , wherein the processor is further configured to initialize the extension by a flow vector that corresponds to location coordinates in the surveillance area near the target.

15. The computer program product of claim 12 , wherein at least one of the following holds true:

extending the lead vector is initialized by a flow vector that corresponds to location coordinates in the surveillance area near the target, and wherein extending the lead vector is performed for directions that go away from the target;

the first intermediate vector and the second intermediate vector are calculated by interpolation, and wherein the interpolation is a bilinear interpolation;

selecting one the intermediate vectors as lead vector is performed for the intermediate vector that represents the larger displacement of the intermediate vectors;

the image frames in the sequence of frames have data coordinates that are pixels;

the movement characteristics includes a movement time (TM) in correspondence to the number of lead vectors, and wherein the movement time (TM) is related to location coordinates of the queue object and of the target;

the characteristics include a queue length;

the characteristics includes the identification of a queue tail as a location in that the flow vectors following the movement characteristics go below a threshold value.