diplomsko delo
Nejc Loboda (Author), Robert Rozman (Mentor)

Abstract

V okviru diplomske naloge smo izdelali sistem za snemanje in beleženje dogajanja v vozilu. Uporabili smo majhen mikroračunalnik Raspberry Pi, na katerega smo priklopili kamero in zunanja tipala za temperaturo, pospeške, položaj, mikrofon ter tipko za izklop. Celoten sistem smo vgradili v vozilo. Podatke s tipal smo zajemali in shranjevali na spominsko SD kartico. V sistem smo vgradili vnaprej naučen model za zaznavanje ostalih vozil v prometu in s pomočjo zajetih podatkov s tipal zaznavali izredne dogodke. Te dogodke smo shranili kot zaznamke, ki kažejo na čas dogodka v videoposnetku. Sistem omogoča enostaven priklop, uporabo in spremljanje dogajanja na mobilni napravi. Delovanje celotnega sistema smo ocenili s preizkusnimi vožnjami. Ugotovili smo, da je sistem v obstoječem stanju zelo uporaben in nudi zanimive funkcionalnosti, ki se lahko v prihodnosti še nadgradijo.

Keywords

Raspberry Pi;snemanje;zaznavanje;kamera;tipala;računalništvo in informatika;visokošolski strokovni študij;diplomske naloge;

Data

Language: Slovenian
Year of publishing:
Typology: 2.11 - Undergraduate Thesis
Organization: UL FRI - Faculty of Computer and Information Science
Publisher: [N. Loboda]
UDC: 004.9(043.2)
COBISS: 98221315 Link will open in a new window
Views: 136
Downloads: 24
Average score: 0 (0 votes)
Metadata: JSON JSON-RDF JSON-LD TURTLE N-TRIPLES XML RDFA MICRODATA DC-XML DC-RDF RDF

Other data

Secondary language: English
Secondary title: System for recording and logging of events in vehicle
Secondary abstract: We have developed a system for recording and logging traffic events in the thesis. We used a small Raspberry Pi microcomputer to which we connected a camera and external sensors for temperature, acceleration, position, microphone and the power button. The whole system was installed in the vehicle. Sensor data was captured and stored on the SD memory card. We integrated a pre-trained model to detect other vehicles in traffic and used the captured data from the sensors to identify unusual events. We stored these events as bookmarks with the time of the event in the video. The system allows easy connection, use and monitoring of the events on the mobile device. The operation of the entire system was evaluated through test drives. We found that the system in its current state is very useful and offers interesting functionalities that can be enhanced in the future.
Secondary keywords: Raspberry Pi;recording;detection;camera;sensors;computer science;computer and information science;diploma thesis;Računalništvo;Univerzitetna in visokošolska dela;
Type (COBISS): Bachelor thesis/paper
Study programme: 1000470
Embargo end date (OpenAIRE): 1970-01-01
Thesis comment: Univ. v Ljubljani, Fak. za računalništvo in informatiko
Pages: 52 str.
ID: 14562752