Human Action Recognition

Course
2021-2022
Semester
2
ECTS
3
Type
Elective
University
UDC

Subject objectives

-Knowledge of recognition techniques applied to the recognition of people, and body parts.

-Analysis and evaluation of human action recognition applications

-Development of tools based on advanced technologies for recognition of human actions

Contents

Detection and tracking of people.
Detection and monitoring of faces, extremities, and other features of interest.
Recognition of postural and behavioral patterns.
Applications of the recognition of human actions.

Basic and complementary bibliography

Basic
I.-O. Stathopoulou, G.A. Tsihrintzis. «Visual Affect Recognition», IOS Press, 2010. ISBN:978-I-60750-596-9.

Premaratne, P. «Human Computer Interaction Using Hand Gestures». Springer 2014. ISBN: 978-981-4585-68-2.

Gong, S.; Xiang, T. «Visual Analysis of Behaviour: From pixels to semantics». Springer 2011. ISBN: 978-0-85729-669-6.

Moeslund, T.B.; Hilton, A.; Krüger, V.; Sigal, L. (Eds.), «Visual Analysis of Humans: Looking at people». Springer, 2011. ISBN: 978-0-85729-996-3.

Salah, A.A.; Gevers, T. (Eds.), «Computer Analysis of Human Behavior». Springer, 2011. ISBN: 978-0-85729-993-2.

Murino, V.; Cristani, M.; Shah, S.; Savarese, S. «Group and Crowd Behavior for Computer Vision». 2017. ISBN: 9780128092767.

Competencies

CE2 – To know and apply machine learning and pattern recognition techniques applied to
computer vision
CE3 – To know and apply the concepts, methodologies and technologies of image and video
analysis
CE4 – To conceive, develop and evaluate complex computer vision systems
CE9 – To know and apply the concepts, methodologies and technologies for the recognition of
visual patterns in real scenes

CB8 – That students are able to integrate knowledge and deal with the complexity of making
judgements based on information that is incomplete or limited, including reflections on social
and ethical responsibilities linked to the application of their knowledge and judgements

CG2 – Ability to analyze a company’s needs in the field of computer vision and determine the
best technological solution for it
G6 – Ability to identify theoretical results or new technologies with innovative potential and
convert them into products and services useful to society
CG7 – Ability to learn autonomously for specialization in one or more fields of study

CT3 – Development of the innovative and entrepreneurial spirit

Teaching methodology

Laboratory practice:
Practice in computer classrooms, learning based on the resolution of practical cases, combining work and autonomous learning with group
work for cooperative learning

Supervised projects:
Realization of presentations of project-oriented work

Guest lecture / keynote speech:
Participatory master classes

See Contingency Plan for Alternative Scenarios.

Evaluation system

-Guest lecture / keynote speech (30):
Demonstration of application knowledge taught in class
Competences: CE2,CE3 CG7

-Supervised projects (40) :
Practical projects related to the subject
Competences: CG2,CG3 CT3

-Laboratory practice (30):
Applied case development practices
Competences: CE4,CE9 CB8

See Contingency Plan for Alternative Scenarios.

Studying time and personal work

Recommended study time for students is about 2 hours per week. Additionally, we estimate that they should spend about 3 hours / week working in a number of assignments. All of these activities add up to around 60h/semester.

Subject study recommendations

Subjects that it is recommended to have taken before:
Fundamentals of Machine Learning for Computer Vision /614535007
Fundamentals of Image Analysis and Processing/614535001
Image Description and Modeling/614535004

Subjects that are recommended to be taken simultaneously:
Visual Recognition/614535005

Observations

Contingency Plan for Alternative Scenarios:

1. Modifications to the contents None.
2.All the used methodologies could be applied on a non-presential basis with the available tools (Moodle, Teams, etc.)
3. Mechanisms for personalized attention to students Continuous attention in Teams, Moodle and email.
4. Modifications in the evaluation Not necessary.
5. Modifications to the bibliography or webgraphy None.