prikaz prve stranice dokumenta SUSTAV ZA NADZOR VOZAČA POMOĆU UGRADBENE RAČUNALNE PLATFORME
  Download
PDF 1.83 MB
master's thesis
SUSTAV ZA NADZOR VOZAČA POMOĆU UGRADBENE RAČUNALNE PLATFORME
2022. urn:nbn:hr:200:034698
Rimal, Rajesh
Josip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Department of Communications
Chair of Electronics and Microelectronics

Cite this document

Rimal, R. (2022). SUSTAV ZA NADZOR VOZAČA POMOĆU UGRADBENE RAČUNALNE PLATFORME (Master's thesis). Retrieved from https://urn.nsk.hr/urn:nbn:hr:200:034698

Rimal, Rajesh. "SUSTAV ZA NADZOR VOZAČA POMOĆU UGRADBENE RAČUNALNE PLATFORME." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2022. https://urn.nsk.hr/urn:nbn:hr:200:034698

Rimal, Rajesh. "SUSTAV ZA NADZOR VOZAČA POMOĆU UGRADBENE RAČUNALNE PLATFORME." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2022. https://urn.nsk.hr/urn:nbn:hr:200:034698

Rimal, R. (2022). 'SUSTAV ZA NADZOR VOZAČA POMOĆU UGRADBENE RAČUNALNE PLATFORME', Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 19 March 2023, https://urn.nsk.hr/urn:nbn:hr:200:034698

Rimal R. SUSTAV ZA NADZOR VOZAČA POMOĆU UGRADBENE RAČUNALNE PLATFORME [Master's thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2022 [cited 2023 March 19] Available at: https://urn.nsk.hr/urn:nbn:hr:200:034698

R. Rimal, "SUSTAV ZA NADZOR VOZAČA POMOĆU UGRADBENE RAČUNALNE PLATFORME", Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Osijek, 2022. Available at: https://urn.nsk.hr/urn:nbn:hr:200:034698

Please login to the repository to save this object to your list.
Metadata
TitleSUSTAV ZA NADZOR VOZAČA POMOĆU UGRADBENE RAČUNALNE PLATFORME
Title (english)DRIVER MONITORING SYSTEM USING AN EMBEDDED COMPUTER PLATFORM
AuthorRajesh Rimal
MentorMarijan Herceg (mentor)
Committee memberMarijan Herceg (predsjednik povjerenstva)
Committee memberMario Vranješ (član povjerenstva)
Committee memberRatko Grbić (član povjerenstva)
GranterJosip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
(Department of Communications)
(Chair of Electronics and Microelectronics)
Osijek
Defense date and country2022-07-14, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Electrical Engineering
Electronics
Abstract
U ovom diplomskom radu predlaže se Sustav za nadzor vozača (DMS) koji se temelji na biheviorističkom pristupu gdje sustav detektira umor i nepažnju vozača na temelju slika dobivenih s kamere postavljene na instrument ploči vozila. Skup podataka za praćenje vozača (DMD) i skup podataka YawDD korišteni su za razvoj modela na osobnom računalu (PC), a isti je model implementiran u Raspberry Pi. Za detekciju lica i lokalizaciju orijentira korištena je metoda MediaPipe Facemesh koja se temelji na konvolucijskoj neuronskoj mreži (CNN). Također, metode poput upotrebe omjera površine preko udaljenosti (ADR), omjera usta (MAR) i Eulerovih kutova korištene su za detekciju oka, stanja usta i položaja glave. Algoritam također izračunava adaptivni prag za MAR, ADR i srednji položaj lica koji će varirati od pojedinca do pojedinca. Razvijeni sustav testiran je i pomoću Raspberry Pi kamere.
Abstract (english)
In this thesis, Driver Monitoring System (DMS) is proposed based on the behavioral approach where the system detects the fatigue and inattention of the driver based on the images obtained from the camera mounted on the vehicle’s dashboard. The driver monitoring dataset (DMD) and YawDD datasets were used to develop the model on a personal computer (PC) and the same model was implemented in the Raspberry Pi. The convolutional neural network (CNN)-based method MediaPipe Facemesh was used to detect a face and the localization of the landmarks. Also, the methods like the use of area over the distance ratio (ADR), mouth aspect ratio (MAR), and Euler angles were used to detect the eye, mouth state, and head position. The algorithm also calculates the adaptive threshold for MAR, ADR, and mean position of a face which will vary from individual to individual. The developed system is also tested using the Raspberry Pi camera.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:200:034698
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 on2022-09-08 06:58:23