Politecnico di Torino (logo)

Indoor Navigation based on the plain browser.

Elchin Fahradov

Indoor Navigation based on the plain browser.

Rel. Giovanni Malnati. Politecnico di Torino, Corso di laurea magistrale in Ingegneria Informatica (Computer Engineering), 2022

PDF (Tesi_di_laurea) - Tesi
Licenza: Creative Commons Attribution Non-commercial No Derivatives.

Download (2MB) | Preview

Today finding any destination in an unfamiliar environment is a struggling process for everyone. Therefore, navigation has become the main problem from the earliest days of human history. In the early periods, people were using different techniques for navigation. With the improvement of technology GPS has been invented and become an inseparable part of our daily lives. However, it’s a fact that today's definition of navigation is not only about the outdoor environments. With the development of architectural structures, humankind began to create massive buildings with all the necessary facilities. The popularity of these kinds of massive architectural structures has created a demand for indoor navigation. This is because GPS technology signals, when used indoors, can be very weak when passing through walls or may not pass at all. Therefore, we need a new approach to find the destination we are looking for in a closed area. Different technologies have emerged to solve the problem of indoor navigation. In our study, we investigated different types of navigation systems for indoor infrastructures. In the initial stage, we did research about already available indoor navigation technologies with their working principles, advantages, and disadvantages. As a result, we have concluded that most of the existing indoor navigation technology requires more resources and cost while configuring it. After getting familiar with existing solutions, we introduced our methodology for the given problem. In this study, we have focused on a visual-based navigation system. The visual-based navigation system uses the device's camera to help scan markers or objects in the environment to determine orientation and position. The QR code was used as a visual marker in our methodology due to its distinctive features that helped us for solving the direction and position problem. While doing our project the first and main struggle we have faced is to convert world point coordinates into camera coordinates. Since it's a fact that objects are recognized in 3D in the real world, but in 2D on computer screens. Therefore, it is important to convert and display the 3D image on a 2D screen. This problem is known as the PnP (Perspective n Point) problem. In our work, we have analyzed this problem in a detailed way and tried to come up with possible solutions. To solve this problem, we used Rust's Lambda Twist library which is one of the fastest and most accurate libraries of all other PnP solvers that we have analyzed. We have also applied the Dijkstra algorithm to find the shortest path. As an experiment, we created an imaginary map with unique coordinates and tested our application with different source and destination points. Based on the experiments and studies, we concluded that our indoor navigation system can be applied in all types of infrastructure with low cost and high performance.

Relators: Giovanni Malnati
Academic year: 2021/22
Publication type: Electronic
Number of Pages: 73
Corso di laurea: Corso di laurea magistrale in Ingegneria Informatica (Computer Engineering)
Classe di laurea: New organization > Master science > LM-32 - COMPUTER SYSTEMS ENGINEERING
Aziende collaboratrici: UNSPECIFIED
URI: http://webthesis.biblio.polito.it/id/eprint/23562
Modify record (reserved for operators) Modify record (reserved for operators)