You are on page 1of 1

DR. M.

AHMAD 1

Assignment No. 2 – 4 Points


Fundamentals of Computer Vision – Deadline Before or on April 30, 2023

I. T HUMBNAILS /RULE / DON ’ T


1) Cheat/copy/plagiarized material
2) Uncited use of any material from anywhere
3) Share/steal any material with/from former or current students
4) Penalties:
• Zero marks for first sharing infringement (both parties)
• Exclusion from the course for second sharing infringement (both parties).

II. Q UESTION N O . 1
Record a video a few seconds long of an object with some texture on it.
1) Track the features using the Harris corner algorithm and record your observation about the algorithm.
2) Track the same object using Scale Invariant Feature Transform (SIFT) and record your observations.

III. Q UESTION N O . 2
1) Dense/Optical Flow algorithm (Lucas Kanade): Analysis of the Optical Flow algorithm and their
built-in functions present in jupyter notebook.
• goodFeaturesToTrack()
• calcOpticalFlowPyrLK()
2) Track the same object in Question No 1 using the optical flow algorithm and record your observa-
tions.

IV. Q UESTION N O . 3
1) Histogram of Oriented Gradients (HoG): Implement HoG on positive (face images) and negative
(none face images) examples for face detection example on jupyter notebook.
• Extract HoG features from positive and negative examples.
• Train the model (KNN and SVM) and do the hard-negative mining.
• Test the model on any of your own image and draw the bounding box on the face.

You might also like