Un-Distracted - App That Prevents Distracted Driving through Facial and Spatial Recognition using CNNs

CSEF · 2023 Computational Systems & Analysis Honorable_mention Award

Overview

This project’s goal is to solve the devastating issue of distracted driving which has caused 30% of all fatal accidents, about 10,000 deaths. To solve this issue, my app can detect a driver that is not focused on the road and alert the driver with a loud sound to make sure they go back to focusing on driving. It also tracks the amount of times a driver is distracted and provides positive reinforcement to help reduce the amount of times the driver is distracted. Using the iPhone’s front facing camera, the app discerns whether the driver is distracted or drowsy through convolutional neural networks under the architecture of Shufflenet V2. The model takes the input image from the live camera feed and uses the weights trained with over 4 gigabytes of data to classify whether the driver is distracted or not. This is in conjunction with Apple’s ArKit to generate a near perfect mesh of points across the face, so that the driver can be detected as distracted even with things covering their face such as sunglasses and masks. Along with the detections, using Firebase (Cloud Server), the app is able to log the progress of the driver’s distractions and the amount of times they are distracted. The model was able to detect and alert distracted driving with 98.26% accuracy and the average loss on the model was 0.01682. This model’s accuracy proves it can detect and alert distracted driving on a large scale while also trying to prevent further distractions from occurring through the tracking system.

Source coverage

This record comes from a published award list, not a complete project archive. Its abstract comes from CSEF's public project showcase as archived by the Internet Archive before judging (https://web.archive.org/web/20230401224130/https://ca-csef.zfairs.com/showcase/ShowcaseInfo?f=838e60b7-ea75-46e8-865c-fde4864244b3); the version presented may differ.

Awards (1)

  • Category Award: HM

Competition history

  • CSEF 2023 Computational Systems & Analysis · Entry S0856

Resources

Related projects

Closest projects by meaning, across every fair and year in the corpus.

Browse more like this

Source: California Science & Engineering Fair public projects

Save projects to your library

Sign in with Google to keep track of projects you find interesting, organized into folders. An account also raises your daily allowance for “Has this been done?”, and lets you create a key for the MCP server with a much higher limit than anonymous use. Browsing stays public.

Continue with Google