Computer Vision Methods Labs

Labs plan

Labs are organized in four main topics: Correspondence problem, Indexing and image retrieval, Object tracking, Convolutional neural networks. Each topic is covered by approximately two to four labs.

Week	Date	Topic	Recording
1	22.2.	Introduction to Image Processing in python using PyTorch.	recording 2022
2	1.3.	Debugging pytorch code.
3	8.3.	Correspondence problem I, detection of the interest points.	recording 2022
4	15.3.	Correspondence problem II, computing local invariant description.	recording 2022
5	22.3.	Correspondence problem III, finding tenative correspondences and RANSAC.	recording 2022
6	29.3.	Correspondence problem, summary.
7	5.4.	Image Retrieval I, BoW TF-IDF
8	12.4.	Image Retrieval II, fast spatial verification.
9	19.4.	Convolutional Neural Networks: training a classifier	recording 2022
10	26.4.	Convolutional Neural Networks II: debugging training process
11	3.5.	Deep metric learning
12	10.5.	Rectors day.
13	17.5.	Tracking I, Kanade-Lucas-Tomasi tracking (KLT tracker)
14	24.5.	Tracking II, KCF tracker. Finishing the assignments

Labs will be accompanied with a simple programming task. Detailed specification of the tasks is described in each of the labs. Students will upload their results and their codes through the BRUTE system.

Each lab will usually consists of three parts:

Discussion on the last lecture. Students will be free to ask any questions related to the last lecture. At the end of this session, a teacher will pose a question to a volunteer/random student. If the student answers correctly, he/she will get a single bonus point.
Working on the current task. Students are free to ask any specific questions, discuss their current results, resolve any programming issues.
Short introduction of the next task. The teacher will briefly introduce the next problem, give some hints and answer possible questions.

Assessment

You are obliged to carry out all programming tasks at least a minimal required quality. All tasks must be carried out individually! You are free to discuss the problems with your colleagues, however the code must be written strictly by yourself. See plagiarism if you are unsure what is allowed.

Evaluation Policy

The points from the labs will contribute to 50 percent of your course evaluation.

There will be 11 tasks awarded with points throughout the semester (a new task will be given out every week in the lab, with the exception of two labs which are intended to help students with debugging). On top of these tasks, there will also be ability to get bonus points in some labs.

Each task has a deadline of 2 weeks and 1 day.

Each task uploaded after the due date is penalized as follows: 0.015pts for every hour after the deadline (= 2.5pts/7days)
The maximum penalty is 60% of the maximum points, e.g. for the task uploaded in 1 month late, you will get < =40%.

Useful Links

Computer vision: Facts & Fiction series
Computer Vision course at CMU
PyTorch & Python development

Course Assistants

Lukáš Neumann	Dmytro Mishkin	Pavel Šuma	Ondřej Drbohlav (lead)

Table of Contents

Computer Vision Methods Labs

Labs plan

Assessment

Evaluation Policy

Useful Links