Bachelor's Thesis

Augmented Reality in Outdoor Environment

Final Thesis 6.02 MB

Author of thesis: Aleksander Postelga

Acad. year: 2025/2026

Supervisor: doc. Ing. Vítězslav Beran, Ph.D.

Reviewer: Ing. Daniel Bambušek

Abstract:

This bachelor's thesis addresses the design and implementation of a mobile augmented reality application for outdoor environments. The system enables a user to place a 3D scene at a specific geographic location and subsequently discover, view, and interact with it using a mobile device. The proposed solution deliberately separates approximate GPS-based localization from precise visual localization, achieving rendering stability and orientation consistency despite outdoor sensor inaccuracies. The application supports compass-guided navigation to placements, surface-detected object anchoring, gesture-based manipulation, physics-based object interactions, and foreground masking via LiDAR depth estimation. Experiments conducted across different devices and outdoor conditions demonstrate that the proposed approach provides sufficiently consistent object orientation across sessions and robust local placement stability.

Keywords:

augmented reality, outdoor environment, mobile AR, localization, SLAM, occlusion, AR interactions

Date of defence

18.06.2026

Result of the defence

Defended (thesis was successfully defended)

znamkaBznamka

Grading

B

Process of defence

Student nejprve prezentoval výsledky, kterých dosáhl v rámci své práce. Komise se poté seznámila s hodnocením vedoucího a posudkem oponenta práce. Student následně odpověděl na otázky oponenta. Komise se na základě posudku oponenta, hodnocení vedoucího, přednesené prezentace a odpovědí studenta na položené otázky rozhodla práci hodnotit stupněm B.

Topics for thesis defence

  1. In what kinds of applications could your solution be used? Have you considered multi-user applications? How far is your solution from a multi-user experience, and what would need to be added to achieve it?
  2. To what extent does your solution depend on a specific phone model (iPhone 14 Pro)? Would it work just as well on other models and without LiDAR?

Language of thesis

English

Faculty

Department

Study programme

Information Technology (BIT)

Composition of Committee

doc. Dr. Ing. Dušan Kolář (předseda)
doc. Ing. Vladimír Janoušek, Ph.D. (místopředseda)
Ing. Radek Hranický, Ph.D. (člen)
Ing. Jiří Matoušek, Ph.D. (člen)
Ing. Zdeněk Materna, Ph.D. (člen)

Aleksander Postelga dedicated himself to the project with great diligence and immense commitment. He demonstrated the ability to work independently, successfully proposed partial solutions, and tackled complex technical difficulties during implementation. Through his exceptional hard work, the student successfully acquired the necessary competencies and delivered a solution that met the expectations.

Evaluation criteria Verbal classification
Informace k zadání

The bachelor's thesis is more difficult. It requires mastering several implementationally non-trivial procedures, ranging from the general application of Augmented Reality (AR) technology and 3D graphics to interacting with virtual objects and utilising mobile device sensors to refine outdoor localisation. The student successfully fulfilled the assignment by designing an outdoor AR system with foreground occlusion, selecting suitable tools, and evaluating the solution through experiments. The final work is rather above average in terms of the scope of the implemented sub-tasks, and the results are highly satisfactory.

Práce s literaturou

The student actively searched for technical resources and materials related to AR. There was a space for improvement in a deeper study of the recommended academic literature, which would have provided a more profound and scholarly understanding of the topic.

Aktivita během řešení, konzultace, komunikace

Throughout the project, Aleksander Postelga was highly active and demonstrated an immense commitment to the topic. He attended consultations always thoroughly prepared and on schedule. Understanding the core challenges and finding professional, methodical solutions occupied the larger part of the project timeline. While it initially took the student longer to grasp the advanced concepts, he gradually became familiar with key problems and focused his attention on specific subtasks.

Aktivita při dokončování

The work on the AR system and data set preparation was carried out continuously according to the schedule, which allowed it to be completed well ahead of the deadline. The final content and the results were properly consulted, and the student incorporated the supervisor's recommendations.

Publikační činnost, ocenění
Points proposed by supervisor: 90

Grade proposed by supervisor: A

Reviewer’s report
Ing. Daniel Bambušek

Mr. Postelga created a functional and technically non-trivial prototype of a mobile AR application for outdoor environments. I particularly appreciate the complete workflow for creating, navigating, and displaying AR objects, the integration with ARKit, LiDAR occlusion, and several interactive 3D models. The overall impression is slightly negatively affected by the technical report's quality, particularly its poor handling of the literature.

Evaluation criteria Verbal classification Points
Náročnost zadání

Evaluation level: obtížnější zadání

The assignment can be considered more difficult because it requires a combination of several non-trivial techniques and procedures, such as localization in outdoor environments, interaction with AR models, and handling occlusions.

Prezentační úroveň technické zprávy

The technical report has a logical structure, well-balanced chapters, and is very readable. However, the theoretical section relies on a limited number of sources, and it sometimes seems that individual sections are merely transcriptions of a single cited source. For example, Section 2.3 is based on a non-technical, marketing-oriented online source and adopts a classification of AR localization types and methods that seems technically inaccurate. The text would be more credible if supported by high-quality sources. I also missed a broader analysis of existing solutions, as the text discusses only three applications, and a more explicit discussion of potential use cases for the solution created in this thesis.

70
Formální úprava technické zprávy

Both formally and typographically, the work is of high quality.

85
Realizační výstup

The implementation is the thesis's strongest part. The author has created a functional application demonstrating a possible use of augmented reality in large outdoor environments. The solution combines coarse geolocation using GPS with local AR sessions, which then display the model in AR within the local space using the ARKit library. The author demonstrates possible applications in four different models with varying user interactions. The application supports model occlusion and its interaction with the real-world environment. The source code is well-structured, and user testing has been conducted properly.

90
Využitelnost výsledků

The solution can serve as a very good base platform for implementing user applications that utilize geolocation and augmented reality (geocaching, Pokémon Go-style games, etc.)

Rozsah splnění požadavků zadání

Evaluation level: zadání splněno

Rozsah technické zprávy

Evaluation level: je v obvyklém rozmezí

Práce s literaturou

The author cites 4 scholarly sources that could be considered relatively old, 1 contemporary scholarly source, and 4 online sources that would be better replaced with the books or scientific publications from which these sources often derive their information. For example, the entire section 2.2 is based on a single source (Azuma, 1999), which, while historically important, should be complemented by the current state of the art, as AR has advanced significantly since then. AR in outdoor environments remains a relevant scientific topic, with numerous contemporary publications.

55
Topics for thesis defence:
  1. To what extent does your solution depend on a specific phone model (iPhone 14 Pro)? Would it work just as well on other models and without LiDAR?
  2. In what kinds of applications could your solution be used? Have you considered multi-user applications? How far is your solution from a multi-user experience, and what would need to be added to achieve it?
Points proposed by reviewer: 80

Grade proposed by reviewer: B

Responsibility: Mgr. et Mgr. Hana Odstrčilová