Perception and Mapping

Code:

M.EEC035

Acronym:

PMAP

Keywords
Classification	Keyword
OFICIAL	Automation and Control

Instance: 2023/2024 - 1S

Active?	Yes
Responsible unit:	Department of Electrical and Computer Engineering
Course/CS Responsible:	Master in Electrical and Computer Engineering

Cycles of Study/Courses

Acronym	No. of Students	Study Plan	Curricular Years	Credits UCN	Credits ECTS	Contact hours	Total Time
M.EEC	41	Syllabus	2	-	6	39	162

Teaching language

Suitable for English-speaking students
Obs.: Material em Inglês; língua de trabalho pode ser Inglês se necessário

Objectives

Perception and Mapping addresses the current challenges of extracting 2D and 3D information, reconstructing and interpreting scenes based on active and passive sensors (or a set of sensors). Examples of application of UC contents include improving the perceptual capacity of autonomous agents (land, air and sea) so that they are able to properly interact with the surrounding environment.

Students who successfully complete this UC must:

-understand and be able to explain the concepts of image and point cloud processing, and the fundamental algorithms for sensory fusion applied to localization and mapping.

- have knowledge of existing methods for visual data analysis and be able to apply them in practical situations;

-acquire skills that allows them to use tools such as ROS, OpenCV and PCL, which implement some of the analyzed algorithms, and implement novel algorithms described in the literature;

-be able to analyze and understand selected scientific articles in the fields of computer vision and mobile robotics.

It is also intended that students shall be able to design and conceive advanced 2D and 3D perception systems.

Learning outcomes and competences

Teaching and learning methods aim the knowledge of the contents referred to in the syllabus, reaching the targeted goals and competencies. The diversity of proposed methodologies aims at enhancing the skills and competencies established, seeking to evidence different levels of analysis, fostering the integration of knowledge. The proposed methods and strategies aim to develop students' knowledge, understanding and skills in processing 2D and 3D information.

The generic skills of teamwork, organization, etc. will be worked on in the group project.

Likewise, the ability to develop computer vision according to existing needs and to apply the most appropriate technological tools, to know, apply and evaluate 2D/3D information will be worked out in the weekly exercises and group project.

The specific skills in perception techniques will be worked during the semester in theoretical-practical classes.

Working method

Presencial

Pre-requirements (prior knowledge) and co-requirements (common knowledge)

Programming skills.

Program

Introduction to Perception and Mapping

Sensors (cameras, LiDAR, Sonar, GPS, Inertial)

 

Image processing and analysis

  Acquisition of digital images of intensity and color

  Geometric and radiometric model of a camera

  Extraction of features and outliers

  Multiple image geometry

 

Processing and analysis of point clouds

   Acquisition of points clouds (active and passive)

   Filters, Feature Extraction and Registration

   

2D and 3D Perception Systems

  Calibration of multisensory systems

  Sensor fusion (KF, Bayes, etc)

  Scenario representation

  SLAM

 

Case Study

Mandatory literature

Peter Corke; Robotics, vision and control. ISBN: 978-3-642-20143-1

Teaching methods and learning activities

Theoretical-Practical Classes: exposition and discussion of the contents of the program, and the resolution of exercises.

Practical assignments: development of programming projects related to perception techniques/algorithms.

Two projects/ assignments will be developed during the semester; these projects must be developed both during classes and at home.

There is also a final project in which each group will present a short report, in article format, and the project will be presented orally.

The final exam is worth 25% of the final classification.

Evaluation Type

Distributed evaluation with final exam

Assessment Components

Designation	Weight (%)
Exame	25,00
Trabalho laboratorial	75,00
Total:	100,00

Amount of time allocated to each course unit

Designation	Time (hours)
Estudo autónomo	40,00
Trabalho escrito	40,00
Trabalho laboratorial	43,00
Total:	123,00

Eligibility for exams

-- University of Porto (UP) regulations.
-- Completion of the practical works (with positive grade)

Calculation formula of final grade

CF = 0.25*E + 0.2*P1+0.25*P2+0.3*P3 

CF - final grade
P1 - assignment 1
P2 - assignment 2
P3 - assignment (final project)
E - exame final


Approval only if:
- P1 >= 9.5
- P2 >= 9.5
- P3 >= 9.5
- E >= 8

Examinations or Special Assignments

Students who have not carried out the practical component during the academic period will have to carry out an equivalent work.

Special assessment (TE, DA, ...)

UP regulations

Classification improvement

P1, P2 and P3 are not possible to be enhanced in the same year.

Observations