國立高雄大學圖資館 |

Language: English

Back

Deep Learning Using Computer Vision ...

Kanagaraj, Nitin.

Deep Learning Using Computer Vision in Self Driving Cars for Lane and Traffic Sign Detection.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Deep Learning Using Computer Vision in Self Driving Cars for Lane and Traffic Sign Detection.
Author:	Kanagaraj, Nitin.
Published:	Ann Arbor : ProQuest Dissertations & Theses, 2019
Description:	43 p.
Notes:	Source: Masters Abstracts International, Volume: 81-03.
Notes:	Advisor: Hicks, David.
Contained By:	Masters Abstracts International81-03.
Subject:	Computer science.
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=13898820
ISBN:	9781085618335

Deep Learning Using Computer Vision in Self Driving Cars for Lane and Traffic Sign Detection.
Kanagaraj, Nitin.

Deep Learning Using Computer Vision in Self Driving Cars for Lane and Traffic Sign Detection. - Ann Arbor : ProQuest Dissertations & Theses, 2019 - 43 p.

Source: Masters Abstracts International, Volume: 81-03.

Thesis (M.S.)--Texas A&M University - Kingsville, 2019.

This item is not available from ProQuest Dissertations & Theses.

In the last few years, the amount of research in the field of self-driving cars has been immense with autonomous vehicles clocking in more than 10 million miles and providing a plethora of data to be trained and tested. The most complex part of training is the use of computer vision for feature extraction and object detection in real-time. There has been a lot of research done on improving the algorithms in image segmentation and keeping the user alert by scanning their facial expression. The proposed idea presents the use of Convoluted Neural Networks using Spatial Transformer Networks and lane detection in computer vision to improve lane detection in real time and to increase the efficiency of autonomous vehicles. The depth of the neural network will help in training the vehicles and during the testing phase the vehicles will learn to make decisions based on the training data. In case of sudden changes to the environment the vehicle will be able to make decisions quickly to prevent damage to lives. Along with lane detection, the self-driving cars must also be able to detect the traffic signs which is done using the Adam Optimizer which runs on top of the LeNet 5 architecture. The LeNet 5 architecture is also compared with the Feed Forward Neural Network. The accuracy of the LeNet 5 architecture was 97% and the accuracy of the Feed Forward Neural Network was 94%. Hence, it is proved that the accuracy of the LeNet5 architecture is better than the Feed Forward Neural Network.

ISBN: 9781085618335Subjects--Topical Terms:

199325
Computer science.

Deep Learning Using Computer Vision in Self Driving Cars for Lane and Traffic Sign Detection.
LDR:02575nmm a2200325 4500 001 570785
005 20200514111959.5
008 200901s2019 ||||||||||||||||| ||eng d
020 $a 9781085618335
035 $a (MiAaPQ)AAI13898820
035 $a AAI13898820
040 $a MiAaPQ $c MiAaPQ
100 1 $a Kanagaraj, Nitin. $3 857489
245 1 0 $a Deep Learning Using Computer Vision in Self Driving Cars for Lane and Traffic Sign Detection.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2019
300 $a 43 p.
500 $a Source: Masters Abstracts International, Volume: 81-03.
500 $a Advisor: Hicks, David.
502 $a Thesis (M.S.)--Texas A&M University - Kingsville, 2019.
506 $a This item is not available from ProQuest Dissertations & Theses.
506 $a This item must not be sold to any third party vendors.
520 $a In the last few years, the amount of research in the field of self-driving cars has been immense with autonomous vehicles clocking in more than 10 million miles and providing a plethora of data to be trained and tested. The most complex part of training is the use of computer vision for feature extraction and object detection in real-time. There has been a lot of research done on improving the algorithms in image segmentation and keeping the user alert by scanning their facial expression. The proposed idea presents the use of Convoluted Neural Networks using Spatial Transformer Networks and lane detection in computer vision to improve lane detection in real time and to increase the efficiency of autonomous vehicles. The depth of the neural network will help in training the vehicles and during the testing phase the vehicles will learn to make decisions based on the training data. In case of sudden changes to the environment the vehicle will be able to make decisions quickly to prevent damage to lives. Along with lane detection, the self-driving cars must also be able to detect the traffic signs which is done using the Adam Optimizer which runs on top of the LeNet 5 architecture. The LeNet 5 architecture is also compared with the Feed Forward Neural Network. The accuracy of the LeNet 5 architecture was 97% and the accuracy of the Feed Forward Neural Network was 94%. Hence, it is proved that the accuracy of the LeNet5 architecture is better than the Feed Forward Neural Network.
590 $a School code: 1187.
650 4 $a Computer science. $3 199325
650 4 $a Automotive engineering. $3 739048
650 4 $a Artificial intelligence. $3 194058
690 $a 0984
690 $a 0800
690 $a 0540
710 2 $a Texas A&M University - Kingsville. $b Electrical Engineering and Computer Science. $3 857472
773 0 $t Masters Abstracts International $g 81-03.
790 $a 1187
791 $a M.S.
792 $a 2019
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=13898820