Monday, November 7, 2022 - 13:00 to 14:30
SCHOOL OF COMPUTER SCIENCE
The School of Computer Science is pleased to present…
MSc Thesis Proposal by: Raghib Barkat Muhib
Date: Monday, November 7, 2022
Time: 1:00 PM - 2:30 PM
Location: Essex Hall, Room 122
Reminder: Two-part attendance mandatory, arrive 5-10 minutes prior to event starting - LATECOMERS WILL NOT BE ADMITTED once the presentation has begun.
Vehicle classification is essential to intelligent transportation systems(ITS). This work proposes a model based on transfer learning, combining data augmentation, for the recognition and classification of local vehicle classes in Canada, drawing inspiration from contemporary deep learning (DL) achievements in image classification. This makes use of the well-known Stanford AI of Vehicles Dataset, which has 16185 photos. The images in this section are divided into 196 kinds of typical vehicles. To increase performance further, additional classification blocks are added to the residual network (ResNet-50)-based model which is being used. Automatic extraction and categorization of vehicle type features will be done in this case. A number of measures like accuracy, precision, recall, etc., will be employed during the analysis to evaluate the results. The proposed model exhibited increasing accuracy despite the vehicles' shifting physical characteristics. In comparison to the current baseline method and the two pre-trained DL systems, AlexNet and VGG-16, our suggested method outperforms them all initially. The suggested ResNet-50 pre-trained model primitively achieves an accuracy of 83% in the classification of native vehicle types, according to outcome comparisons. We have also compared this by running VGG-16 where we are getting an accuracy of 81%. Along with this vehicle classification ,we have implemented number plate detection and smart vehicle counter systems which all together will make our transport system better than ever before.
Keywords: Vehicle type classification, Deep learning, Convolutional Neural Network, Transfer learning, ResNet-50, VGG-16 , ANPR, OpenCV, EasyOCR.
MSc Thesis Committee:
Internal Reader: Dr. Dan Wu
External Reader: Dr. Esam Abdel-Raheem
Advisor: Dr. Imran Ahmad
MSc Thesis Proposal Announcement
5113 Lambton Tower 401 Sunset Ave. Windsor ON, N9B 3P4 (519) 253-3000 Ext. 3716 email@example.com