DRIVEALIVE
a 3 week project, May 2024

Team:
Ivery Chen, Dave Song, Hadley Dalton, Healey Koch
Role:
UIUX Design, Frontend Engineering
Tools:
Figma, Python, Javascript
01
ContextHow to design an interface that detects drowsy driving?
Drowsy driving ranks among the top causes of traffic accidents, significantly affecting road safety. Providing early warnings to sleepy drivers could prevent numerous accidents on the roads.
According to data collected by the U.S. Department of Transportation over the past decade, car accidents, including both injuries and fatalities, are increasing. It is imperative that we use our abilities as software engineers to promote safer driving.
For our purpose, we want to create a site that allows one to upload/stream a video and it suggests whether someone is drowsy driving or not.
02
ResearchHow do we determine what makes someone ‘drowsy’?
We determine how many drowsy blinks one exhibits in a short, seconds-long clip. First, the system identifies the face area in every frame of the video within each second. Then, it pinpoints the eye area using a facial landmarks detector. Next, it calculates and analyzes the eye aspect ratio for each frame. Afterward, three types of classifiers—linear SVM and sequential neural network—are used to enhance accuracy. The data is then classified to determine whether the driver's eyes are open or closed. The system detects closed eyes for a set period within each second, tallying the amount of drowsy blinks persisting within or throughout the seconds. The amount of drowsy blinks per minute is then quantified. More than even one drowsy blink should urge you to reconsider driving.
03
Process1. Trained a CNN on images of open and closed eyes
2. Used Haarcascades to locate the face and isolate the eyes, which were then sent to the CNN for classification
3. If the eyes were closed for 15 frames (or half a second) it was counted as a “drowsy” blink

Model Architecture
04
SolutionWe created a web page with UI to what the real product would look like.

Model Architecture