- Recent Announcements (Last modified approximately
at
- Welcome to the course. Note: Most links will not work.
- Our first class is on Tuesday, Jan 3 in CC
103 (CSE bldg adjacent to SOM, first floor). Please try
to be in the room by 6:00 PM.
- Please complete
this
Google form (with sso login) before the stated
deadline (on the form).
- I recognize some registrations require instructor
approval. Please complete google form in order to make
this happen.
- All announcements are moved to Piazza. Please
monitor Piazza.
|
-
Informal Course Overview: In this course we build on
what you have learnt (or learned:-) in an earlier digital imaging
processing course. (Some of you may have been unable
to take the class in Odd semester 2022-2023, we will
see what we can do).
Given the above, in this course we will cover a
proper subset of (in no particular order) [We will
do "old CV" and "new CV" similar to last offerings
("deep learning") .]
- Human face and human body
- Features
- Single and Multi-view geometry
- Optical Flow and Motion
- Shape from Shading
-
Segmentation and region growing
- Reading and presenting research papers.
- Knowledge representation and inference
- Object recognition (quickly) and tracking
(hopefully)
- Texture classification and recognition
(in passing?)
- Activity recognition (in passing?)
- Computational Photography and super-resolution
-
Course Prerequisites (aka "who is
allowed"):
- The primary (informal) prequisite is that you
should be a student, not a
test-taker. (What's the difference?)
- CS663 (Digital Image Processing) or equivalent
offered by CSE is a declared
prerequisite (will be relaxed this
semester)
- In addition, students are expected to
have basic programming skills
(programming with loops, pointers,
structures, recursion), linear algebra
and matrix methods. (We will freshen
up as required.)
- Audits are discouraged for all and prohibited for
non-PhD candidates.
- The course is open (modulo the above)
to any UG/PG in CSE (and folks who are
going into IDDDP in CMInDS)
- That said, the general goal is to
"enable" all students who wish to be
part of this course. Please note that
we are talking about students, and not
test-takers.
- Non-CSE (e.g. EE) will be
considered. However, it's not kosher
to repeat this course again (say after
doing in EE) to jack up CPI.
|
- What I will discuss next
- Faces.. Format of the tasks.
|
- Topics and some key points:
This is just a stub from last time. Monitor Piazza for the
current offering.
Date    
  | Topic | Some key points |
04 Jan |
Course Logistics, Policies, Intro to course |
Slides Read course web page
carefully |
07 Jan |
Direct Linear Transform |
|
11 Jan |
Why It works |
Slides |
14 Jan |
Camera matrices |
Read
Slides 1-17 |
18 Jan |
Planar Homography |
Slides
Slides
|
21 Jan |
TBD |
Read Tensorflow Tutorial |
25 Jan |
Projective 3-Space |
Slides |
28 Jan |
P3 Lines, P2 Transforms |
Slides |
01 Feb |
Cross Ratio |
Slides
|
04 Feb |
Height of a Person |
Slides
|
08 Feb |
Introducing Features |
Slides
Scale Space, SIFT
|
11 Feb |
Features |
Slides
|
15 Feb |
TBD |
Slides
|
18 Feb |
TBD |
Slides
|
19 Feb |
Midsem Start |
No slides
|
26 Feb |
Midsem ends |
No slides
|
01 Mar |
Maha Siva Ratri Holiday |
Camera Calibration |
04 Mar |
Calibration |
Slides
|
08 Mar |
Basics of DNL |
Slides
|
11 Mar |
Object Detection via DNL |
Slides
|
15 Mar |
Learning to generate 3D |
Slides
|
18 Mar |
Holi |
Color |
22 Mar |
Calibration |
Lec 18
|
25 Mar |
Optical Flow |
Slides
Slides
|
29 Mar |
Optical Flow |
Slides
Slides
|
01 Apr |
Optical Flow |
|
05 Apr |
Basics of DNL |
See link above |
08 Apr |
Basics of Deep Neural Network (DNL) |
See link above |
12 Apr |
Basics of Deep Neural Network (DNL) |
See link above |
15 Apr |
Good Friday |
Object Detection via DNL |
?? Apr |
Stereo definition, triangulation |
Slides |
?? Apr |
8 point algorithm, Correspondence-1 |
Slides
Slides |
?? Apr |
Fundamental matrix |
|
?? Apr |
Camera Matrices Stereo correspondence
from Calculus of Variations |
Slides
Slides |
?? Apr |
Camera matrices from F Stereo correspondence
via DP |
Slides |
Slides
?? Apr |
Essential Matrix and Rectification |
Slides
Slides |
?? Apr |
Shape from shading |
Slides |
?? Apr |
Shape from shading |
Slides |
|
- Tasks. Assignments are not
optional. Piazza will have the latest on these
tasks. (The following is a stub from previous offerings).
- Upload assignments to moodle. For group
assignment, lowest (lexicographic) roll
number submits inlab.
In the situation that
moodle is down around the deadline, make a
copy, and upload it to Google drive or
Dropbox, and send link. Do not send the
assignment via email. Except for the first
assignment, all others will be posted on Piazza
- Lab zero has been posted on Jan 17
- Lab Two: Tensor Flow Basics
- Lab Three: Scanning like CamScanner
- Lab Four: Visual attendance!
- Lab Five: Camera calibration
- Lab Six: Focal length and VR
- Lab Seven: Basic CNN
- Lab Eight: Lifting 2D to 3D
- Lab Nine: Adversarial Networks
- Lab Ten: GAN
- Lab Eleven: Features
- Lab Twelve: Siamese Network
- Lab Thirteen: Deep Net
- Lab Fourteen: TBD
- Lab Fifteen: Project PartA
- Lab Fifteen: Project PartB
|
- Notes on evaluation.
- Grading. This is tentative.
The final version will be available on Piazza and these can be
safely discarded after drop/add deadline.
- Class participation (Viva): Pass/Not Pass (5%-10%) (starts after course
drop/add).
- Regular Task X: 1--3 programming assignments: (approx x%)
- Regular Task Y: 1--3 home work: (approx y% where x + y ~= (40-60))
- No midsemester exam in the midsem week (consider the periodic
tasks as midsem).
- Instructor Viva (not for everyone) to ensure you understand what you are
doing. Viva can reduce marks for some people in group assignments.
- Piazza Points: This will be used for generously tipping you when you are
on the grade border.
- This is important . By default, I will asume that
you will adhere to the following pledge (aka honour code)
I pledge on my honour that I have not given or received any
unauthorized assistance on this assignment or any previous task.
and will write and sign this on EVERY submission that carries points.
(You can use (Gita/Koran/Bible/Old Testament) (pick one) instead of
"honour" in the above line.
If you are not clear what unauthorized assistance means, please talk
to me.
- Collaboration:
By default, i.e., unless specified otherwise, you may discuss
general ideas behind tasks with people in the course.
What does this mean?
- In any case, you are not to discuss this with external people
-- anyone other than TA -- outside your course.
- Needless to say, you are not allowed to take previous year's
question papers or assignments. This will also apply in the future
after you finish with this course when your juniors ask you.
- Any electronic discussion must happen via Piazza. No WA.
- By default, please feel free to take things from the
Internet but do not plagiarize from the Internet, i.e., if you do
end up having to use external sources you MUST cite these clearly
- For SOME tasks, you may be expressly prohibited to look for
solutions from the Internet. In such cases,
finding answers to problems on the Web or from other outside
sources (these include anyone not enrolled in the class) is
strictly forbidden. (Typically this is the general idea behind
midsemester and final exams.)
- Some tasks will be in groups. You can discuss within this group,
i.e., for these tasks, the group is the unit
- In all cases, you cannot borrow something for which you claim
points. More specifically, if you submit something, and out of the
100% you submitted, 80% is from the Internet, that is fine -- only if you
give proper acknowledgment. You will be entitled to be graded out of
100% even if your work of 20% is purely yours.
But if you do not include acknowledgment for the 80% but you
acknowledging only 30%, then you are falsely claiming credit
The same situation if you are discussing your task with people on,
say, WA.
Violation of this policy is considered serious and will be dealt with
strictly. By reading these lines, you
agree to these terms :-)
- Even if you miss the task deadline, you have to submit your
assignment to prevent getting a fail grade. (There is no guarantee
that you will get any credit for it.)
- If you miss a submission deadline or an exam, your marks will
be rescaled (based on other assignments) ONLY in exceptional
circumstances (medical reason for example). These must be approved
by me BEFORE the due date in writing or via email. The default is
that you get zero.
- The following is true for all electronic submissions. Late
submission carry a leaky exponential penalty. Assignments submitted
within the first 29 minutes after the deadline are considered 'on
time'. However any
assignment that is late by more than 29 minutes will attract the
penalty (table is as follows, intervals are semi-closed, i.e. open on
the right). Thus an assignment submitted 31 minutes late w.r.t. the
original, stated submission deadline will attract 20% penalty.
Late submission in
hours | 1-2 | 2-4 | 4-6 | 6-8 | 8-10 | 10-14 | 14-24 | late for more
than 24 hours |
Penalty | 20% | 25% | 30% | 35% | 52% | 65% | 85% | 100% (You still have to submit it) |
- Grade revision policy: Students have a habit for asking for more
points on their exams. This is understandable. Please use the
following policy for clarification of corrected papers:
- If you have any questions on the grading, you must bring
it to the attention of the professor concerned within 72 hours of
receipt or the next lecture, whichever is earlier.
- Please study the model answers before you question a decision.
If you need to appeal a decision, please note that the instructor
now has the ability to review prior marking, and thus continues to
have the right to revise the marks of questions other than the
ones you are debating.
- I request that you do not ask frivolous questions. In
particular, questions of the form "I think I should be given partial
credit" are not welcome. You must instead use the objective criterion
"Model answer states 2 marks for this step; I have written this step;
please reevaluate".
|
- Texts/References (DL references to come in later).
- Text: Computer Vision by Ponce and Forsyth
- Other References in no particular order
- Trucco & Verri. Introductory Techniques for 3-D Computer
Vision
- Rick Szeliski.
Computer Vision: Algorithms & Applications
(available free)
- Hartley and Zissmeran. Multiple view geometry
|
|
- Solutions I used to post solutions,
but nowadays I hand them
out in class. Solutions may be occasionally posted and deleted asynchronously
(in order that students from other courses do not suffer/benefit).
|
-
Student Driven Course Evaluation.
-
The anonymous
midterm course evaluation process
should happen week after midsem.
|