prikaz prve stranice dokumenta Uočavanje i izlučivanje dinamičkih objekata stereovizijskim sustavom i radarima na vozilu
No public access
master's thesis
Uočavanje i izlučivanje dinamičkih objekata stereovizijskim sustavom i radarima na vozilu
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2015. urn:nbn:hr:168:356821
Obrvan, Marko
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Obrvan, M. (2015). Uočavanje i izlučivanje dinamičkih objekata stereovizijskim sustavom i radarima na vozilu (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:356821

Obrvan, Marko. "Uočavanje i izlučivanje dinamičkih objekata stereovizijskim sustavom i radarima na vozilu." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2015. https://urn.nsk.hr/urn:nbn:hr:168:356821

Obrvan, Marko. "Uočavanje i izlučivanje dinamičkih objekata stereovizijskim sustavom i radarima na vozilu." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2015. https://urn.nsk.hr/urn:nbn:hr:168:356821

Obrvan, M. (2015). 'Uočavanje i izlučivanje dinamičkih objekata stereovizijskim sustavom i radarima na vozilu', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 10 November 2024, https://urn.nsk.hr/urn:nbn:hr:168:356821

Obrvan M. Uočavanje i izlučivanje dinamičkih objekata stereovizijskim sustavom i radarima na vozilu [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2015 [cited 2024 November 10] Available at: https://urn.nsk.hr/urn:nbn:hr:168:356821

M. Obrvan, "Uočavanje i izlučivanje dinamičkih objekata stereovizijskim sustavom i radarima na vozilu", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2015. Available at: https://urn.nsk.hr/urn:nbn:hr:168:356821

Metadata
TitleUočavanje i izlučivanje dinamičkih objekata stereovizijskim sustavom i radarima na vozilu
Title (english)Detection and extraction of dynamic objects using a stereo vision system and radars on a vehicle
AuthorMarko Obrvan
MentorIvan Petrović (mentor)
Committee memberIvan Petrović (predsjednik povjerenstva)
Committee memberNikola Mišković (član povjerenstva)
Committee memberMarija Seder (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2015-07-17, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
U ovom radu obrađena je nova metoda detekcije vozila zasnovana na izgledu vozila u sceni, koristeći stereo vid i radare. U svrhu korištenja sustava za detekciju vozila kao pomoć vozaču, ispravno detektiranje i praćenje vozila je od visokog značaja. Kako bi takav sustav radio, često se predlaže korištenje više rada s komplementarnim sposobnostima detekcije. S time na umu, unutar ovog rada se koristila kombinacija kemere i dvije radarske jedinice kako bi se postigle detekcije. Detekcije se prvo generiraju samostalno unutar kamere, što na kao izlaz daje pozicije vozila. Nakon toga se lista očitanih pozicija iz slike preklapa s listom radarskih očitanja u svrhu stvaranja pouzdanije detekcije. Detekcija na osnovi stereo vida se zasniva na (i) detekciji i obradi rubova, unutar koje se također koristi informacija o disparitetu dviju kamera (ii) izvlačenja svih kontura s potencijalnim oblikom vozila (iii) generiranje pozicije vozila u sceni. Uzevši u obzir da se preklapanje detekcija od strane radarskih očitanja i očitanja stereo vida vrši tek na kraju algoritma, može se reći da se radi s fuzijom visoke razine. Analiza rada algoritma se vršila u stvarnoj radnoj okolini, visoke dinamičnosti i pod značajnim utjecajem osvjetljenja uzrokovani sunčanim vremenom.
Abstract (english)
In this work we proposed a novel method for appearance based vehicle detection by employing stereo vision system and radar units. In the vein of utilizing advanced driver assistance systems, detection and tracking of moving objects or particularly vehicles, represents an essential task. For the merits of such application, it has often been suggested to combine multiple sensors with complementary modalities. In accordance, we utilize a stereo vision and two radar units, and fuse the corresponding modalities at the level of detection. Firstly, the algorithm executes the detection procedure based on stereo image solely, generating the information about vehicles’ position. Secondly, the final unique list of vehicles is obtained by overlapping the radar readings with the preliminary list obtained by stereo system. The stereo vision–based detection procedure consists of (i) edge processing plugging in also the information about disparity map (ii) shape based vehicles’ contour extraction (iii) preliminary vehicles’ positions generation. since the radar readings are examined by overlapping them with the list obtained by stereo vision, the proposed algorithm can be considered as high level fusion approach. We analyze the performance of the proposed algorithm by performing the real-world experiment in highly dynamic urban environment, under significant illumination influences caused by sunny weather.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:356821
Study programmeTitle: Computing
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsClosed access
Terms of useLicence In copyright icon
Public note
Created on2018-02-06 10:58:05