prikaz prve stranice dokumenta Algoritam za autonomnu vožnju zasnovan na prepoznavanju prometnih znakova
  Download
PDF 2.58 MB
master's thesis
Algoritam za autonomnu vožnju zasnovan na prepoznavanju prometnih znakova
2019. urn:nbn:hr:200:288558
Mijić, David
Josip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Department of Communications
Chair of Multimedia Systems and Digital Television

Cite this document

Mijić, D. (2019). Algoritam za autonomnu vožnju zasnovan na prepoznavanju prometnih znakova (Master's thesis). Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek. Retrieved from https://urn.nsk.hr/urn:nbn:hr:200:288558

Mijić, David. "Algoritam za autonomnu vožnju zasnovan na prepoznavanju prometnih znakova." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2019. https://urn.nsk.hr/urn:nbn:hr:200:288558

Mijić, David. "Algoritam za autonomnu vožnju zasnovan na prepoznavanju prometnih znakova." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2019. https://urn.nsk.hr/urn:nbn:hr:200:288558

Mijić, D. (2019). 'Algoritam za autonomnu vožnju zasnovan na prepoznavanju prometnih znakova', Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 25 April 2024, https://urn.nsk.hr/urn:nbn:hr:200:288558

Mijić D. Algoritam za autonomnu vožnju zasnovan na prepoznavanju prometnih znakova [Master's thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2019 [cited 2024 April 25] Available at: https://urn.nsk.hr/urn:nbn:hr:200:288558

D. Mijić, "Algoritam za autonomnu vožnju zasnovan na prepoznavanju prometnih znakova", Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Osijek, 2019. Available at: https://urn.nsk.hr/urn:nbn:hr:200:288558

Please login to the repository to save this object to your list.
Metadata
TitleAlgoritam za autonomnu vožnju zasnovan na prepoznavanju prometnih znakova
Title (english)Autonomous driving algorithm based on traffic signs recognition
AuthorDavid Mijić
MentorMario Vranješ (mentor)
Committee memberMario Vranješ (predsjednik povjerenstva)
Committee memberRatko Grbić (član povjerenstva)
Committee memberMarijan Herceg (član povjerenstva)
GranterJosip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
(Department of Communications)
(Chair of Multimedia Systems and Digital Television)
Osijek
Defense date and country2019-09-12, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Artificial Intelligence
Abstract
U ovom diplomskom radu razvijen je algoritam za upravljanje modelom vozila zasnovan na prepoznatim prometnim znakovima. YOLO algoritam korišten je za prepoznavanje određenih prometnih znakova, a parametri algoritma za prepoznavanja prometnih znakova trenirani su na označenim slikama iz kreirane baze podataka određenih prometnih znakova. Programski okvir ROS korišten je za upravljanje modelom vozila u CARLA simulatoru otvorenog koda. Čvor za primanje graničnih okvira detektiranih objekata u spremnik pohranjuje zadnjih 25 detektiranih prometnih znakova i na temelju znaka koji se najviše puta pojavljuje u spremniku šalje se naredba za upravljanje modelom vozila. Rješenje je testirano na slikama prikupljenim iz simulatora na kojima prepoznaje prometne znakove u različitim vremenskim uvjetima. Manji problemi se pojavljuju prilikom detekcije sličnih znakova, ali ti problemi su uspješno riješeni korištenjem spremnika za detekciju.
Abstract (english)
In this graduate thesis, an autonomous driving algorithm based on traffic signs recognition is developed. For a traffic sign recognition, the YOLO algorithm is used and weights for a traffic sign recognition algorithm are trained with a created database of specific traffic signs. ROS framework is used for controlling a vehicle model in CARLA open source simulator. A node used for receiving bounding boxes of detected objects uses a buffer in which he stores last 25 detected traffic signs and based on a traffic sign which appears the most time in a buffer, a command for controlling vehicle model is sent. The solution is tested on images from real life traffic and images collected from a simulator. The results are satisfying for different weather conditions. Small problems are noticed while detecting similar traffic signs, but these problems are successfully solved using a detection buffer.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:200:288558
Study programmeTitle: UNIVERSITY STUDY AUTOMOBILE COMPUTER AND COMMUNICATION
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka automobilskog računarstva i komunikacija (magistar/magistra inženjer/inženjerka automobilskog računarstva i komunikacija)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2020-03-02 13:17:07