Image segmentation, feature description and object tracking form the foundation of many successful applications of computer vision. The objective of this task is for you to become familiar with these techniques and their implementation in OpenCV.

Given a video with several (up to 3) objects of interest, the tasks are to detect the objects and track them through the video.

1. You will need a video that contains objects that appear in most video frames, and in particular the first frame. This first frame may be used as a model frame.
2. You can then use feature descriptors to match objects in the model frame to those in each frame (image) of the sequence.
3. You should be able to display the estimated object locations in each frame in the video.
4. You should also display the ongoing object trajectories, based on the estimated object locations in each frame in the video.