Schedule Students of the course Upload system Discussion forum
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.
Lab | Date | Topic |
---|---|---|
1 | 21.2. | Introduction to Image Processing in MATLAB. |
2 | 28.3. | Correspondence problem I, detection of the interest points. |
3 | 7.3. | Correspondence problem II, computing local invariant description. |
4 | 14.3. | Correspondence problem III, finding tenative correspondences and RANSAC. |
5 | 21.3. | Correspondence problem, summary. |
6 | 28.3. | Indexing I, image representation with set of visual words. TF-IDF weighting |
7 | 4.4. | Indexing II, fast spatial verification, query expansion. |
8 | 11.4. | Indexing III, complete pipeline for image retrieval in big databases. |
9 | 18.4. | Convolutional Neural Networks I. |
10 | 25.4. | Convolutional Neural Networks II. |
11 | 2.5. | Tracking I, Kanade-Lucas-Tomasi tracking (KLT tracker). |
12 | 9.5. | Tracking II, Correlation tracking (KCF tracker). |
13 | 16.5. | “Rektorský den” (A day without teaching at the CTU). |
14 | 23.5. | Consultations on exam questions. |
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:
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.
Your participation on the labs is not mandatory, however we will not provide any extra consultations besides those during the labs.
The grading points from the labs will contribute to 50 percent of your course evaluation. It is required to obtain at least half of the points for each programming task.
Each task uploaded after the due date is penalized as follows:
Upload late by 6 - 24 hours ⇒ -10% of the points, 24 - 48 hours ⇒ -25% of the points and finally 48 - 72 hours ⇒ 40% of the maximum points. Tasks not delivered until 72 hours after the due date (i.e. three days after the due date) without a relevant excuse will not be accepted and automatically lead to failing the course.