Oct 27, 2020   10:22 p.m. Sabína, pamätný deň - Deň černovskej tragédie
Academic information system

Persons at STU


This page displays all publicly accessible information about the desired person. Some information about the person's occupation and offices may be hidden.

Ing. Miroslav Laco
Identification number: 72202
University e-mail: miroslav.laco [at] stuba.sk
 
2511V00  Applied Informatics D-AI
FIIT D-AI den [year 3]
Doctoral type of study, full-time, attendance method form
3rd year of study

Contacts
     
          
Final thesis
     
Projects     Publications     Placements     Supervised theses
     

Basic information

Basic information about a final thesis

Type of thesis: Diploma thesis
Thesis title:
Generating a saliency map with focus on different aspects of human visual attention
Written by (author):
Department:
Thesis supervisor:
Opponent:
Final thesis progress:
Final thesis was successfully defended.


Additional information

Additional information about the final thesis follows. Click on the language link to display the information in the desired language.

Language of final thesis:
English

Slovak        English

Title of the thesis:
Generating a saliency map with focus on different aspects of human visual attention
Summary:Visual attention modelling is under extensive research throughout the past years. We analyse the current state-of-the-art in the visual attention modelling in the analytical part of this thesis. We propose a novel method to conduct user studies for research of human visual attention in real world environments from the egocentric perspective of view, building upon state-of-the-art in the visual attention modelling. We introduce a novel and complete method proposal for the user studies setup in a laboratory. To meet our specified goals, we use various hardware equipment and introduce our own algorithms and procedures based on the principles of image processing and computer vision. We created a novel dataset for studying human visual attention in real environments from the egocentric perspective of view during the extensive user studies following our proposed method. One of the biggest assets of the proposed method and the created dataset is the possibility to study aspects affecting visual attention that were not possible to study before. Based on the previous work in the field, we decided to conduct a research on the depth influence (distance between the observer and the observed object) on visual attention in real environments using the novel dataset. We claim that the aspect of depth influence on human visual attention can be applied on existing visual attention models as a saliency coefficient. We apply the results of our research on an existing saliency model, summarize up the results and conclude future possible improvements.
Key words:visual attention modelling, saliency map, egocentric video, computer vision

Display and download files

To display the final thesis assignment form click on the Display the final thesis assignment form icon. The following icons - Final thesis, Thesis appendices, Supervisor's review, Opponent's review - relate to the final thesis and can be downloaded. They could be displayed on condition they have been inserted and are available publicly.

Parts of thesis with postponed release:

Final thesis (final thesis appendices) unlimited
Reviews for final thesis unlimited