Distance and speed predictive analytics based on dashcam video /
Syarifah Nabilah Syahirah Binti Syed Abd Wahab
- xv, 41 pages : illustrations ; 1 CD-ROM.
Center for Mathematical Sciences
Bachelor of Applied Science In Data Analytics With Honour -- Universiti Malaysia Pahang – 2023
Includes bibliographical references
Dashcam is a device that capture the surroundings of a vehicle and is commonly utilised as evidence in road crimes and accidents. Malaysian drivers who have difficulty estimating the distance and speed between vehicles due to human error might be prevented by utilising dashcam data, preventing an accident. The purpose of this research is to develop a predictive modelling for estimating the distance and speed of vehicles on the road. The goal is to reduce the incidence of accidents and crimes that occur on the road. The study was conducted using deep learning techniques such as Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN) methods. The dataset used in this study was provided by Cybersecurity Malaysia and it consists of dashcam video footage captured by Malaysian drivers. The dashcam footage was used to analysed the real-life distance and speed between vehicles, which be used to make more accurate predictions. Based on the research conducted using deep learning techniques such as LSTM and CNN models on the provided dashcam video footage, the evaluation results revealed moderate accuracy indicating room for improvement. The study provided insights into vehicle speed distributions and distances, paving the way for future advancements in distance and speed predictive analytics. The findings from this study will help to enhance road safety in Malaysia by providing valuable insights and improving drivers’ ability to estimate distance and speed, potentially reducing accidents and crimes on the road.
THE0010030 (Local)
Center for Mathematical Sciences--Dissertations
Universities and colleges--Dissertations Final Year Report--Dissertations