Developing An Object Detection Camera Vision System for Unpredictable Scenarios in Autonomous Vehicles Using Convolutional Neural Network (CNN) Based Image Processing

A tétel rövid nézete
dc.contributor.advisorSarvajcz , Kornél
dc.contributor.authorIsmail, Beshr
dc.contributor.departmentDE--Műszaki Kar
dc.date.accessioned2025-09-04T16:48:40Z
dc.date.available2025-09-04T16:48:40Z
dc.date.created2024-05-06
dc.description.abstractThe development of autonomous cars faces challenges in sensor dependability despite the substantial advances in sensing technology. Convolutional Neural Networks (CCNs) is an important algorithm in identifying object detection obstacles in decision-making. In addition, they excel in image processing and object detection tasks due to their trainable parameters and gradient descent approaches. The goal of this thesis project is to enhance object identification in autonomous cars in unexpected conditions, namely identifying construction zones on roadways to improve safety and reliability. Using a pre-trained MobileNetV2 SSD model, the research examines several learning rate schedulers and optimization approaches implemented in Pytorch, including StepLR, MultiStepLR, ExponentialLR, CosineAnnealingLR, SGD, and ASGD. The study reveals that while simpler approaches like StepLR and MultiStepLR outperform others in terms of training loss reduction, prioritizing simplicity and ease of implementation, more complex techniques like CosineAnnealingLR and ReduceLROnPlateauLR offer advantages in specific scenarios. Moreover, ASGD consistently outperforms SGD in convergence speed and validation accuracy, underscoring the importance of selecting appropriate optimization methods tailored to the task at hand.
dc.description.courseMechatronical Engineeringen
dc.description.degreeMSc/MA
dc.format.extent68
dc.identifier.urihttps://hdl.handle.net/2437/397332
dc.language.isoen
dc.rights.accessHozzáférhető a 2022 decemberi felsőoktatási törvénymódosítás értelmében.
dc.subjectCNN, Learning rate, schedulers, optimization
dc.subject.dspaceInformatics::Computer Science
dc.subject.dspaceEngineering Sciences::Electrical Engineering
dc.titleDeveloping An Object Detection Camera Vision System for Unpredictable Scenarios in Autonomous Vehicles Using Convolutional Neural Network (CNN) Based Image Processing
dc.title.translatedObjektumészlelő kameralátás rendszer fejlesztése előre nem látható forgatókönyvekhez autonóm járművekben konvolúciós neurális hálózaton (CNN) alapuló képfeldolgozás segítségével
Fájlok
Eredeti köteg (ORIGINAL bundle)
Megjelenítve 1 - 1 (Összesen 1)
Nincs kép
Név:
Thesis report.pdf
Méret:
3.93 MB
Formátum:
Adobe Portable Document Format
Leírás:
This is the thesis report of my thesis project.
Megjelenítés
Engedélyek köteg
Megjelenítve 1 - 1 (Összesen 1)
Nincs kép
Név:
license.txt
Méret:
1.69 KB
Formátum:
Item-specific license agreed upon to submission
Leírás:
Letöltés
Gyűjtemények
Theses (Department of Electrical Engineering and Mechatronics)