Search In this Thesis
   Search In this Thesis  
العنوان
HardwareandParallelimplementationofArtificial IntelligenceAlgorithms/
المؤلف
Alshiemy, Mohammed AttaAllahMohammed.
هيئة الاعداد
باحث / محمد عطاء الله محمد الشيمي
مشرف / محمد محمود احمد طاهر
مشرف / شريف محمد سيف
مناقش / محمد محمود احمد طاهر
تاريخ النشر
2023.
عدد الصفحات
98p.:
اللغة
الإنجليزية
الدرجة
ماجستير
التخصص
الهندسة
تاريخ الإجازة
1/1/2023
مكان الإجازة
جامعة عين شمس - كلية الهندسة - عندسة الحاسبات والنظم
الفهرس
Only 14 pages are availabe for public view

from 98

from 98

Abstract

Computer vision is an application of artificial intelligence. It is an interdisciplinary scientific field that deals with how a computer can gain high-level understanding from a digital image or video from an engineering perspective. It seeks to understand and automate tasks that can be performed by the human visual system. These include vision tasks. Computer methods for obtaining, processing, analyzing, and understanding digital images and extracting high-dimensional data from the real world in order to produce digital or symbolic information. For example, in decision formulas, the scientific discipline of computer vision is concerned with the theory behind artificial systems that extract information from images. Image data can take many forms, such as video sequences, views from multiple cameras and multidimensional data from a 3D scanner or medical scanning device. The computer vision technology system seeks to apply its theories and models to building computer vision systems. Sub-fields of computer vision include scene reconfiguration, event detection, video tracking, object recognition, 3D position estimation, learning, cataloging, motion estimation, visual servo, and scene modeling. 3D and photo recovery.
The lane detection algorithm is a computer vision image and has been applied in au- tonomous driving systems and smart vehicles, where the lane detection system is respon- sible for marking lanes in a complex road environment. At the same time, lane detection plays an important role in the lane departure warning system of the vehicle. The imple- mented lane detection algorithm is mainly divided into two steps: edge detection and lane detection.
Implementation steps include:
1- Extensive study of the road lane detection algorithm. 2- Implementation of the algorithm on the FPGA.
3- Implementation of the algorithm by parallel programming of the GPU. 4- Trying to improve the performance of the algorithm.
5- Comparing the performance of the algorithm between the two methods in terms of energy consumption, the time spent to implement the algorithm, and the amount of resources used to implement the algorithm.
The thesis is divided into five chapters, in addition to lists of contents, tables, figures, and a list of references