How to retrieve the contour points - convert in to vector using opencv ?

Question

How to retrieve the contour points - opencv ?

My Image has three Objects ( irregular shape ) i have found the contour of above three objects.

**My declaration - Contours **

vector<vector<Point>> contours;

So i got the object co-ordinates like below

contours.[size] = 3
         [capacity ] = 14
         +[0] {size = 330 }
         +[1] {size = 240 }
         +[2] {size = 654 }

here i have three contours, with size of 330, 240,654

Now my Doubt is how to Copy the each contour points of 3 objects to vector ?

I want to use this contour points in calcOpticalFlowPyrLK function as prevPts

Or what can be done ?

Answer 1

_{- A little bit more explanation of my above comment.}

calcOpticalFlowPyrLK() can directly use vector<Point> or vector<Point2f> for parameter prevPts.

prevPts – vector of 2D points for which the flow needs to be found; point coordinates must be single-precision floating-point numbers.

That said, you only need to use contours[0], contours[1] and contours[2] for the 3 objects (they are of type vector<Point>) and pass them to calcOpticalFlowPyrLK().

Answer 2

herohuyongtao gave you the correct answer. You should give him recognition by selecting his answer as the correct answer.

I'll just add a small explanation : your contours is a vector of vector. It has 3 elements, and each of these elements is a vector of points (accessible by using .x and.y). That is exactly what is required by prevPts. By sending contour[i] to the function you are sending the i-th vector of points. See here :http://docs.opencv.org/modules/video/doc/motion_analysis_and_object_tracking.html