Raspodijeljena Android aplikacija za prikaz vožnje unatrag zasnovana na računalnom vidu i tri pametna telefona

undergraduate thesis

• Title (english): Distributed Android Application for Car Reversing Based on Computer Vision and Three Smartphones
• Author: Aleksandar Parenta
• Mentor: Dejan Škvorc (mentor)
• Committee member: Dejan Škvorc (predsjednik povjerenstva)
• Committee member: Josip Jukić (član povjerenstva)
• Committee member: Ivan Grubišić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2024-07-12, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Tema ovog rada je bio razvoj raspodijeljene aplikacije za pomoć u vožnji unazad. Zasniva se na ideji da se koriste tri uređaja kako bi s jednog dobili snimku iza vozila i prikazali je na drugom uređaju unutar vozila, pritom koristeći treći uređaj kao svojevrsni detektor koji bi prepoznao vožnju unazad. Između tri uređaja se uspostavlja Wi-Fi direct peer-to-peer veza te se njom šalje video i kontrolni signali. Za prepoznavanje vožnje unazad koristi se uređaj s kamerom usmjerenom prema mjenjaču... More automobila te koristeći tehnologije računalnog vida utvrđuje je li mjenjač u pozicija za vožnju unazad. Detekcija mjenjača je ostvarena Googleovom knjižnicom za Android ML Kit. Less

Abstract (english)

The goal of this project was the development of a distributed Android application for assisting in driving in reverse. It is built upon the idea of using three connected devices in order to take video from the back of the car and display it on a device inside the car in visibility of the driver. Concurrently, we would be using the third device as a detector of sorts which would be used to detect driving in reverse. The three devices are connected using a Wi-Fi Direct peer-to-peer connection... More which is used for exchanging video and command signals. In order to detect driving in reverse a device is used in such a manor that we place it in a position in the car from where it can see the gear shift. From there it uses computer vision to detect whether the gear shift is in reverse position. For object detection, Google's Android library ML Kit is used. Less

• Keywords: računalni vid; video prijenos; Wi-Fi direct; Android; pomoć u vožnji; kamera; strojno učenje; analiza slike
• Keywords (english): computer vision; video-streaming; Wi-Fi direct; driving assistance; camera; machine learning; image analysis
• Language: croatian
• URN:NBN: urn:nbn:hr:168:481190
• Study programme: Title: Computing; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access
• Created on: 2024-10-12 21:45:50