To predict when vehical has stopped based on the visual input using opencv c++ [closed]

edit

A vehicle is stopped when N car positions are equal : detect the car and measure postion. Start to write some code and come back with a real opencv problem

If context is autonomous driving and embedded camera in the car, one possible solution is to look at optical flow.

i have completed optical flow. any suggestion, what to do futhure to get frames and to print stop on the frame when a car stops

// By y += 5, x += 5 you can specify the grid 
            for (int y = 0; y < Roi.rows; y += 20) {          //50 is the distance between two grid points
                for (int x = 0; x < Roi.cols; x += 20)
                {
                    // get the flow from y, x position * 10 for better visibility
                    const Point2f flowatxy = flow.at<Point2f>(y, x) * 10;
                    // draw line at flow direction
                    line(Roi, Point(x, y), Point(cvRound(x + flowatxy.x), cvRound(y + flowatxy.y)), Scalar(255, 0, 0));
                    // draw initial point
                    circle(Roi, Point(x, y), 1, Scalar(0, 0, 0), -1);


                }

            }

            // draw the results
            namedWindow("image", WINDOW_AUTOSIZE);
            imshow("image", original);.

}

When the displacement flow is almost null, you can print a text with cv::putText()?