prikaz prve stranice dokumenta Sustav za automatsko prepoznavanje i klasifikaciju automobila u prometu
Access restricted to students and staff of home institution
master's thesis
Sustav za automatsko prepoznavanje i klasifikaciju automobila u prometu
2021. urn:nbn:hr:179:151216
Bralić, Niko
University of Split
Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture

Cite this document

Bralić, N. (2021). Sustav za automatsko prepoznavanje i klasifikaciju automobila u prometu (Master's thesis). Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture. Retrieved from https://urn.nsk.hr/urn:nbn:hr:179:151216

Bralić, Niko. "Sustav za automatsko prepoznavanje i klasifikaciju automobila u prometu." Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2021. https://urn.nsk.hr/urn:nbn:hr:179:151216

Bralić, Niko. "Sustav za automatsko prepoznavanje i klasifikaciju automobila u prometu." Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2021. https://urn.nsk.hr/urn:nbn:hr:179:151216

Bralić, N. (2021). 'Sustav za automatsko prepoznavanje i klasifikaciju automobila u prometu', Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, accessed 14 November 2024, https://urn.nsk.hr/urn:nbn:hr:179:151216

Bralić N. Sustav za automatsko prepoznavanje i klasifikaciju automobila u prometu [Master's thesis]. Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture; 2021 [cited 2024 November 14] Available at: https://urn.nsk.hr/urn:nbn:hr:179:151216

N. Bralić, "Sustav za automatsko prepoznavanje i klasifikaciju automobila u prometu", Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, Split, 2021. Available at: https://urn.nsk.hr/urn:nbn:hr:179:151216

Please login to the repository to save this object to your list.
Metadata
TitleSustav za automatsko prepoznavanje i klasifikaciju automobila u prometu
Title (english)System for automatic recognition and classification of cars in traffic
AuthorNiko Bralić
MentorJosip Musić (mentor)
GranterUniversity of Split
Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture
Split
Defense date and country2021-06-01, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Basic Technical Sciences
Automatics
Abstract
Sustav za automatsko prepoznavanje i klasifikaciju automobila u prometu je uređaj čiji je zadatak samostalno u realnom vremenu iz dostupnog video signala detektirati automobil, prepoznati registarsku pločicu, odrediti boju te model i marku automobila. U radu je detaljno opisan princip rada konvolucijskih neuronskih mreža koji su temelj realizacije praktičnog dijela rada. Opisane su radicionalne metode poput Viola-Jones algoritma, a nakon toga i moderne metode detekcije objekata. Korišteni su jednostupanjski detektori čiji se rad temelji na konvolucijskim neuronskim mrežama. Automobili se detektiraju pomoću YOLOv4 detektora. Potom izlaz iz YOLO-a prosljeđuje se za daljnju klasifikaciju. Boja se određuje pomoću KNN algoritma, a model i marka automobila pomoću SSD detektora. Posljednje je detekcija registarske tablice pomoću OpenCV metode pa se znakovi s tablice čitaju pomoću Tesseract-a. Upravo zbog jednostavnosti i brzine rada ovih podsustava, izabrani su za rad na Raspberry Pi ugradbenom računalu. Informacije o automobilu ispisuju se na monitoru. Cijeli sustav testiran je na slikama i na videozapisu. Točnost detekcije automobila iznosi 88,5%, a klasifikacija modela iznosi 78,5%. Točnosti boje iznosi 71,5%, a 51,5% je točnost tablice. Sustav radi brzinom od 1 slike u sekundi (1fps). Nedostatci i prednosti cijelog sustava su opisani te dana su moguća poboljšanja sustava za daljnji razvoj.
Abstract (english)
The system for automatic recognition and classification of cars in traffic is a device whose task is to independently in real-time from the available video signal to detect the car, recognize the license plate, determine the color and model and make the car. The paper describes in detail the principle of operation of convolutional neural networks which are the basis for the realization of the practical part of the work. Traditional methods such as the Viola-Jones algorithm are described, followed by modern methods of object detection. Single-stage detectors based on convolutional neural networks were used. Cars are detected using the YOLOv4 detector. The output from YOLO is then forwarded for further classification. The color is determined using the KNN algorithm, and the model and make of the car using an SSD detector. The last is the detection of the license plate using the OpenCV method, so the characters from the table are read using Tesseract. Precisely because of the simplicity and speed of operation of these subsystems, they were chosen to work on a Raspberry Pi embedded computer. Car information is printed on the monitor. The entire system was tested on images and video. Car detection accuracy is 88,5% and model classification is 78,5%. Color accuracy is 71,5% and 51,5% is licence plate accuracy. The system operates at 1 image per second (1fps). The disadvantages and advantages of the whole system are described and possible improvements of the system for further development are given.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:179:151216
Study programmeTitle: Systems and Control
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka automatike i sustava (magistar/magistra inženjer/inženjerka automatike i sustava)
Type of resourceText
File originBorn digital
Access conditionsAccess restricted to students and staff of home institution
Terms of useLicence In copyright icon
Created on2021-10-11 11:38:10