Automated Inattention Detection Using Computer Vision for Road Safety - Engineering Assignment Help

Assignment Task

Introduction
Road safety has been a major concern ever since the invention of motor vehicles. Every year, it is estimated that road accidents claim upto 1.25 million people, which rounds up to 3,400 casualties every 24 hours (Wegman 2017) . One of the major causes of road accidents is driver fatigue or inattention (W.H.O 2018) . The current road safety measures have marginally helped to curb the rate of deaths relative to the population size but still below the Sustainable Development Goal (SDG) target of 50%
reduction of casualties by 2020 (W.H.O 2018) . Drink-driving has been attributed to causing 5-35% of all the road accidents (W.H.O 2018)

Several actions and measures have been proposed and implemented to reduce the number of fatalities by boosting vehicle safety, improving road infrastructure and increasing child restraint use for child occupants. Laws against drunk driving have been enacted and enforced and contributed to significant drop in drunk driving incidences but there is room for improvement.  Information technology and engineering inventions has enabled strides to be made to boost road safety by incorporating computer vision, Internet of Things, Cloud technology and Artificial intelligence (Abbas and Alsheddy 2021). 
Detection and mitigation using computer vision helps to provide a quick and preventable strategy that might help many drivers to receive a sound alert or warning before a disaster or risk. A basic visual detection technology has components that collects numerous data from driver or vehicle and applies a classification algorithm before availing the results to the driver.

Goals
The goal of this project is to achieve the following:
Combining DBN and HMM to create a robust driver detection system.
The proposed system should capture the temporal information and the interactive link between the facial landmarks.
Having a dataset that compares inattention and attention videos of different drivers to reduce the margin of error. 

Methodology
Driver inattention can either be due to fatigue, distraction or drowsiness (Saini, Saini et al. 2014)  but can have the same catastrophic effects of decreased driving performance and high probability of crashing. The knowledge-based approach of fatigue detection has been criticized as being inaccurate because of the if-then rules from the expert and considering the complexity of describing inattention (Weng, Lai et al. 2016). The uncertainties can be captured using the proposed DBN and HMM technique. The training data should provide all the knowledge necessary without subjective parameter tuning.

This Engineering Assignment has been solved by our Engineering experts at My Uni Paper. Our Assignment Writing Experts are efficient to provide a fresh solution to this question. We are serving more than 10000+ Students in Australia, UK & US by helping them to score HD in their academics. Our Experts are well trained to follow all marking rubrics & referencing style.
Be it a used or new solution, the quality of the work submitted by our assignment experts remains unhampered. You may continue to expect the same or even better quality with the used and new assignment solution files respectively. There’s one thing to be noticed that you could choose one between the two and acquire an HD either way. You could choose a new assignment solution file to get yourself an exclusive, plagiarism (with free Turnitin file), expert quality assignment or order an old solution file that was considered worthy of the highest distinction.