prikaz prve stranice dokumenta Algoritam za detekciju prepreka unutar vozne trake i prilagodbu brzine
  Download
PDF 2.66 MB
master's thesis
Algoritam za detekciju prepreka unutar vozne trake i prilagodbu brzine
Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2019. urn:nbn:hr:200:233358
Ljepić, Srđan
Josip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Department of Computer Engineering and Automation
Chair of Automation and Robotics

Cite this document

Ljepić, S. (2019). Algoritam za detekciju prepreka unutar vozne trake i prilagodbu brzine (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:200:233358

Ljepić, Srđan. "Algoritam za detekciju prepreka unutar vozne trake i prilagodbu brzine." 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:200:233358

Ljepić, Srđan. "Algoritam za detekciju prepreka unutar vozne trake i prilagodbu brzine." 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:200:233358

Ljepić, S. (2019). 'Algoritam za detekciju prepreka unutar vozne trake i prilagodbu brzine', Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 15 March 2025, https://urn.nsk.hr/urn:nbn:hr:200:233358

Ljepić S. Algoritam za detekciju prepreka unutar vozne trake i prilagodbu brzine [Master's thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2019 [cited 2025 March 15] Available at: https://urn.nsk.hr/urn:nbn:hr:200:233358

S. Ljepić, "Algoritam za detekciju prepreka unutar vozne trake i prilagodbu brzine", 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:200:233358

Please login to the repository to save this object to your list.
Metadata
TitleAlgoritam za detekciju prepreka unutar vozne trake i prilagodbu brzine
Title (english)Algorithm for detecting obstacles within the lane and speed adjustment
AuthorSrđan Ljepić
MentorRatko Grbić (mentor)
Committee memberRatko Grbić (predsjednik povjerenstva)
Committee memberMarijan Herceg (član povjerenstva)
Committee memberMario Vranješ (član povjerenstva)
GranterJosip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
(Department of Computer Engineering and Automation)
(Chair of Automation and Robotics)
Osijek
Defense date and country2019-09-26, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Artificial Intelligence
Abstract
Tema ovog diplomskog rada je izrada algoritma za detekciju prepreka unutar vozne trake i prilagodbu brzine vozila. Algoritam se temelji na obradi slika koje se dobivaju s kamere montirane na prednjoj strani vozila pomoću ROS-a. Obrada slika obavljena je metodama računalnog vida, koje su ostvarene pomoću programskog jezika C++ i biblioteke OpenCV. Kada je slika dohvaćena, izvršavaju se metode predobrade slike, kao i detekcija rubova kako bi se smanjio šum. Osim toga, koristi se RANSAC algoritam... More pomoću kojeg se definira područje vozne trake koje se koristi za klasifikaciju i estimaciju udaljenosti od prepreke ako ona postoji, kako bi se pomoću ROS-a omogućilo zaustavljanje vozila. Prilikom verifikacije korišten je Carla simulator, gdje je zaključeno da algoritam na slikama vrlo precizno detektira udaljenost od prepreke. Analizom simulacija vožnje utvrđeno je da algoritam zbog nedovoljne brzine obrade video okvira bez dodatnog proširenja nije prikladan za izvođenje pri većim brzinama vozila Less
Abstract (english)
The topic of this thesis is the development of an algorithm for obstacle detection within the lane and adjusting vehicle speed. The algorithm is based on the processing of images obtained from a camera mounted on the front of the vehicle using ROS. Image processing was done using computer vision methods, which were accomplished using the C++ programming language and the OpenCV library. Once the image is retrieved, image pre-processing methods are performed as well as edge detection to reduce... More noise. Moreover, a RANSAC algorithm is used to define the lane area used to classify and estimate the distance from an obstacle, to stop the vehicle by using ROS if necessary. Carla simulator was used for verification, where it was concluded that the algorithm on pictures detects the distance from the obstacle very accurately. Analyzing the results of driving simulations, it is concluded that due to insufficient processing speed of the video frames without future work, the algorithm is not suitable for execution at higher vehicle speeds. Less
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:200:233358
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
RepositoryFaculty of Electrical Engineering, Computer Science and Information Technology Osijek
Created on2020-01-02 09:51:38
accessibility

closeAccessibilityrefresh

If you wish to permanently save changes, click on Save, if not - your settings will be reset when you restart the browser.