Feature tracker Instead of finding feature points independently in multiple
images and then matching them, find features in the first image of a video or image sequence and
then re-locate the corresponding points in the next frames using either search and gradient descent
(Shi and Tomasi 1994) or learned feature detectors (Lepetit, Pilet, and Fua 2006; Fossati,
Dimitrijevic, Lepetit et al. 2007).
When the number of tracked points drops below a threshold or
new regions in the image become visible, find additional points to track.
(Optional) Winnow out incorrect matches by estimating a homography (6.19–6.23) or
fundamental matrix (Section 7.2.1).
(Optional) Refine the accuracy of your matches using the iterative registration algorithm
described in Section 8.2 and Exercise 8.2.
Please upload a ZIP file containing the following files:
1. All your code files, including any helper files/dependencies.
2. A README file detailing how to run your code along with any compilation instructions.
3. A 2-Page technical report containing the following sections:
4. A short description of the algorithm
5. A description of any code/algorithms that were used/re-used by you for your
6. A few examples of results from your implementations, comparison with the original
implementation (if needed).
7. A general discussion of lessons learned based on your experiments with the algorithm. E.g.
What did you struggle with, issues faced while implementing the code, scopes for and/or
proposed improvements, etc.
Your code will be tested on different test inputs and graded based on the progress of your approach
on these test inputs. A demo session will be scheduled for evaluating your implementation.
Please ensure code is in C/C++, Python, or Matlab. Solutions have to be self-sufficient and not
dependent on other computer vision code, such OpenCV or Matlab vision package, other than for
reading, writing or displaying images.