Content, progress and pedagogy of the
module
Purpose:
The purpose of this course is to equip the student with knowledge
and skills about how to analyse the content of data, especially
images and video, and how to make decisions based on the
analysis.
Learning objectives
Knowledge
- Must have knowledge about the building blocks in a generic
classification system
- Must have knowledge about different colour representations
- Must be able to understand the principles of point- and
neighbourhood processing
- Must be able to understand what a BLOB is and how it can
be extracted
- Must be able to understand how moving objects can be segmented
in a video sequence
- Must be able to understand the concept of a multidimensional
feature-space.
- Must be able to understand the principle behind Bayes rule and
how a classifier can be derived here from
- Must be able to understand how to assess a classification
system
Skills
- Must be able to apply point processing methods like grey-level
mapping, histogram stretching, thresholding and image
arithmetic
- Must be able to apply neighbourhood processing methods like
median filter, mean filter and edge detection
- Must be able to apply morphologic operations like erosion,
dilation opening and closing
- Must be able to suggest/select relevant features and methods
for extracting these
- Must be able to apply Mahalanobis distance
- Must be able to apply dimensionality reduction methods to a
feature space
Competences
- Must be able to design and implement processing methods to
solve a give problem
- Must be able to design and implement a simple classification
system
Type of instruction
See the general description of the types of instruction
described in the introduction to Chapter 3.
Exam
Exams
Name of exam | Robotic Perception |
Type of exam | Written or oral exam |
ECTS | 5 |
Assessment | Passed/Not Passed |
Type of grading | Internal examination |
Criteria of assessment | The criteria of assessment are stated in the Examination
Policies and Procedures |