
Advanced Methods of Signal, Image and Video Processing
Code: 104367Credits: 6
| Degree programme | Type | Course |
|---|---|---|
| Data Engineering | OP | 4 |
Contact lecturer
- Name :
- Debora Gil Resina
- Email :
- debora.gil@uab.cat
Teaching staff
- Debora Gil Resina
Group languages
You can consult this information at the end of the document.
Prerequisites
It is recommended that the student have knowledge and skills in
-
programmingthe Python programming language
-
Signal, Image and Video Processing
-
Statistical validation
-
Computer Learning and Deep Learning
Objectives
Approximately every decade there is a technological tsunami that transforms multiple industries. Artificial Intelligence (AI) is this wave that is sweeping the current technological world. If you've ever wondered:
-
how do computers perform face detection in crowds?
-
How do video calling apps blur the background or replace the background with other images?
-
How do autonomous cars move safely in an urban environment?
-
How is the ball followed with such precision in televised sporting events such as tennis, soccer and basketball?
-
can we know the most effective cancer treatment from multimodal patient data?
-
can we know the emotions of a person with a smart watch and a video?
-
How do machines learn to speak?
If we have aroused your curiosity, this course is what you need. In this course we will learn about topics in Computer Vision such as Object Tracking, Volume Processing, Personalized Medicine, Face Detection, Optical Flow, Human Pose estimation and many more.
Unlike other computer vision courses, this course approaches computer vision in a more practical, experiential and intuitive way. Its main component is a set of projects that must be developed by students divided into teams. All that is needed is a working knowledge of the Python programming language.
We will use OpenCV which is the largest and most popular computer vision library in the world. It is used by thousands of companies, products and devices and is tested every day for scalability and performance. We will also learn to design and adapt specific networksand to choose which is the most appropriate processing method according to the requirements and restrictions of each application.
In summary, Advanced methods of signal, image and video processing is an eminently practical and interdisciplinary subject that is situated on the bridge between artificial intelligence and the real world and that aims to cross this bridge in both directions.
Knowledge:
Describe and relate the phases into which the solution to a signal processing analysis problem is divided.
Identify the advantages and disadvantages of computer vision and signal processing algorithms.
Solve real problems related to computer vision techniques.
Understand the results and limitations of vision techniques in different case studies.
Knowing how to choose the most appropriate computer vision algorithm to solve a given task.
Knowing how to choose the most appropriate computer vision techniques to solve contextualized problems.
Skills:
Recognize situations in which the application of signal processing algorithms may be adequate to solve a problem.
Analyze the problem to be solved and design the optimal solution applying the techniques learned.
Write technical documents related to the analysis and solution of a problem.
Program the basic algorithms to solve the proposed problems.
Evaluate the results of the implemented solution and assess possible improvements.
Defend and argue the decisions made in solving the proposed problems.
Competences
Search, select and manage information and knowledge responsibly.
Conceive, design and implement the most appropriate data acquisition system for the specific problem to be solved.
Develop critical thinking and reasoning and know how to communicate them effectively, both in one's own languages and in English.
That students have the ability to gather and interpret relevant data (usually within their area of study) to make judgments that include reflection on relevant issues.
Learning outcomes
Search, select and manage information and knowledge responsibly.
Develop critical thinking and reasoning and know how to communicate them effectively, both in one's own languages and in English.
Design an image and video acquisition system and apply the basic methods of computer vision to specific problems.
Choose the most appropriate knowledge representation methods for the extraction of the objects present in the scene, image or video and their subsequent analysis.
Extract and analyze the movement of a video (tracking of objects, characteristic points along a video, etc.)
Learning outcomes
- Students must be capable of collecting and interpreting relevant data (usually within their area of study) in order to make statements that reflect social, scientific or ethical relevant issues.
- Generate innovative and competitive proposals in professional activity and research.
- Demonstrate sensitivity towards ethical, social and environmental topics.
- Students must develop the necessary learning skills to undertake further training with a high degree of autonomy.
- Choose and modify the most suitable computational learning methods for the requirements of the health sciences sector.
- Choose and interpret the most suitable predictive models for environmental management in Smart Cities.
Contents
1 - Introduction to Computer Vision and OpenCV
2 - Methods based on extraction and selection of characteristics
3 - Methods based on Deep Learning
4 - How to choose the most suitable method. Design and Experimental Validation.
5 - Image Processing and Analysis. Segmentation and Recognition
6 - Processing and Analysis of temporal signals. Video (tracking), time series (biometric signals)
7 - 3D Volume Processing and Analysis.
8 - Multimodal Data Processing and Analysis.
Learning activities and methodology
| Title | Hours | ECTS | Learning outcomes |
|---|---|---|---|
| Personal work | 115 | 4.6 | |
| Team working seminars | 20 | 0.8 | |
| Lectures | 10 | 0.4 |
The management of the teaching of the subject will be done through the Campus Virtual (http://cv.uab.cat/),which will serve as a management tool for the work teams, make the corresponding deliveries, view grades, communicate with teachers, etc.
The project
The course will follow a teaching learning methodology called Project Based Learning (PBL). The ABP methodology aims to empower and motivate the student in their learning. Groups of between 5 and 6 students will be formed who will be tasked with carrying out a set of projects (of medium size) throughout the semester. There will be weekly monitoring and both group and individual tutoring of the students.
The projects are set by the teaching staff so that they meet the following conditions: be as real as possible; be treatable using elementary tools; not have a standard solution algorithm associated with it.
On the other hand, it is essential to understand that it is not about finding an algorithm that works in 100 x 100 of the cases - often there is no such thing - but simply about \"giving a reasonable solution proposal\".
Projects must develop each team with the maximum possible autonomy. Each team will be assigned a tutor who will follow the evolution but in principle will refrain from imposing their ideas. On the other hand, the student must be clear that it is not a question of looking for the 'solution' of the problem in other places, but of making an original contribution. This does not mean that you have to give up the information that may exist in the bibliography or on the Internet; but when it is used, the teacher must be informed and explain it in memory.
The realization of the project must end in a program and a final report. In addition to delivering it in written form,the results of this report can be exposed in oral presentation. Both, written memory and oral presentation, should be directed mainly to the entity, surely hypothetical, that would have proposed the problem. As a general rule, technicalities will be relegated to specific sections of the written report.
In the oral presentations of the projects, the entire class is expected to attend, and that they intervene through questions and observations.
Assessment
Continuous assessment activities
| Title | Weight | Hours | ECTS | Learning outcomes |
|---|---|---|---|---|
| Individual Note | 30% | 2.5 | 0.1 | 1, 4 |
| Group Note | 70% | 2.5 | 0.1 | 1, 2, 3, 5, 6 |
Given that most of the work revolves around a set of projects that are developed throughout the course, the evaluation is continuous, and does not provide for the single evaluation system.
Evaluation Methodology
At the end of each project, students will make an oral presentation of the project and will deliver a report of the work carried out. Both will be evaluated by the teachers of the subject, whether or not they are the tutors. The evaluation of each project will have a group (70%) and an individual (40%) part.
Group Mark (70%). The group grade will be obtained from the assessment of the report of each project and the code delivered. The degree of technical difficulty, reproducible experimental design, analysis of metrics and interpretation of results will be assessed. The report must include a section specifying the contribution of each member of the group and what use has been made of AI.
For each project, the use of specific methodologies may be requested that constitute basic knowledge and skills that the student must have acquired in the resolution of the proposed problem. The code must allow you to execute a use case and can be used to verify that the students have correctly developed the project,
Individual Mark (30%). Continuous individual evaluation based on class monitoring, contribution to the project and answers to the teacher's questions about the project. These questions will be asked either in a small oral or written session.
Marks
Each project will have a grade that will be calculated as follows:
Project Grade = 0.7 * Group Grade + 0.3 * Individual Grade
The final grade will come from the weighted average of the grades of the projects carried out. The weighting will be the same for all projects
To pass the subject, all the following requirements must be met:
- The final grade must be greater than or equal to 5
- have delivered all the projects.
- The grade for all projects must be greater than or equal to 4
To distinguish between 'fail' and 'not presented', a deadline is set for students to withdraw from the assessment, in which case they will appear as 'not presented'. To unsubscribe, it will be necessary to notify the teacher, in writing or by email, and obtain an acknowledgment of receipt.
Recovery:
In the event that any of the projects has a grade of less than 4, it may be resubmitted on the day that is set as a retake exam in the schedules published by the coordination on the school's website
Honors: Awarding an honors grade is the decision of the teaching staff responsible for the subject. UAB regulations indicate that MH can only be awarded to students who have obtained a final grade equal to or greater than 9.00 and their number cannot exceed 5% of the total number of students enrolled.
In the event that the number of students with a grade greater than or equal to 9 is more than 5% of the total enrolled, the criteria to be applied in the order listed below will be the following:
- Those with the highest Individual Grade are prioritized.
- Priority is given to those with the highest Companys Co-evaluation Grade.
- Priority is given to those with the highest Class Co-assessment Grade.
Grades review procedure
Students will have the right to review the grades published in the place and on the days indicated.
Irregularities on the part of the student, copying and plagiarism
Without prejudice to other disciplinary measures deemed appropriate, and in accordance with current academic regulations, irregularities committed by a student that may lead to a change in grade will be graded with a zero (0). For example, plagiarism, copying, letting copy. An assessment activity will involve failing that assessment activity with a zero (0). Assessment activities graded in this way and for this reason will not be recoverable. If it is necessary to pass any of these evaluation activities to pass the subject, this subject will be suspended directly, without the opportunity to recover it in the same course.
Use of AI
AI should be used as a learning support tool, in no case can it replace the student's learning process. If it is detected that the text of the reports is made exclusively with AI without any input from the student, it will not be corrected. If the code is made with AI, it is the student's responsibility to understand the mechanisms used and verify their functionality.
Bibliography
Forsyth & Ponce, Computer Vision: A Modern Approach, Pearson, 2002, ISBN 0130851981
Computer vision, Linda G. Shapiro and George C. Stockman.
Introductory techniques for 3-D computer vision, Emanuele Trucco and Alessandro Verri.
Software
Python with OpenCV libraries, pytorch. Eventually Matlab. As far as possible, it will facilitate access to clusters of GPUs and CPUs
Course groups and languages
The information provided is provisional until November 30. After this date, you will be able to consult the language of each group through this link. To access the information, you will need to enter the course CODE
| Type of teaching | Group | Language | Semester | Shift |
|---|---|---|---|---|
| (PAUL) Classroom practices | 81 | Catalan/Spanish | first semester | morning-mixed |