Please use this identifier to cite or link to this item:
|Title:||Detecting driver inattentiveness using deep learning approach||Authors:||Chong, Bryan Kuo Wei||Keywords:||Engineering::Electrical and electronic engineering||Issue Date:||2022||Publisher:||Nanyang Technological University||Source:||Chong, B. K. W. (2022). Detecting driver inattentiveness using deep learning approach. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/157970||Project:||A3147-211||Abstract:||The leading cause of road traffic accidents in Singapore, as well as many countries all over the globe is distracted driving. The deaths and injuries associated with such accidents occur when something unexpected happens on the road and the motorists in question are not able to react in time due to their engagement in acts of distracted driving. Over the years, this phenomenon has prompted individuals to adopt a more technical approach through the development of algorithms to aid in the detection of distracted driving behavior, in an effort to reduce the number of accidents. With the advent of deep learning concepts, much research has been conducted to analyze and identify the driver’s behavior using visual imagery in order to determine if it is safe or unsafe driving. A common approach is the use of Convolutional Neural Networks (CNN or ConvNet), and many have achieved a 90% (or more) behavioral detection accuracy. However, there are certain challenges that impede the improvement in detection accuracy of an algorithm. In this project, the performance of CNN algorithms with varying levels of fine tuning will be compared and analyzed. This project aspires to increase the behavioral detection accuracy as much as possible to combat the rising problem of distracted driving.||URI:||https://hdl.handle.net/10356/157970||Fulltext Permission:||restricted||Fulltext Availability:||With Fulltext|
|Appears in Collections:||EEE Student Reports (FYP/IA/PA/PI)|
Files in This Item:
|Detecting Driver Inattentiveness Using Deep Learning Approach.pdf|
|Final Year Report||2.62 MB||Adobe PDF||View/Open|
Updated on Dec 5, 2022
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.