Distracted Driver Detection and Alert System using Deep Learning
Author(s):
A.S.Muthanandha Murugavel, Hemakarthika.M, Reena Rethiga.R, Tharini.R
Keywords:
Abstract
Driver distractedness and interruption are the primary drivers of street mishaps, a significant number of which bring about fatalities. At present, interruption location frameworks for street vehicles are not yet broadly accessible or are restricted to explicit reasons for driver distractedness, for example, driver weariness. Research endeavors have been made to screen drivers' attentional states and offer help to drivers. The current work of occupied driver recognition is worried about a restricted arrangement of interruptions (Mainly phone utilization). In this venture, a strong driver interruption discovery framework that extricates the driver's state from the accounts of a Windshield camera utilizing Deep Learning based Faster Region Convolutional Neural Network (FRCNN). This venture utilizes the state ranch diverted driver identification, which contains four classes: calling, messaging, looking behind, and ordinary driving. The fundamental component of the proposed arrangement is the extraction of the driver's body parts, utilizing profound learning-based division, prior to playing out the interruption discovery and grouping task. The typical exactness of the proposed arrangement surpasses 96% on our dataset. The class actuation map (CAM) of our proposed strategy is abstractly more sensible, which would upgrade the unwavering quality and make sense of capacity of the model.
Article Details
Unique Paper ID: 156032

Publication Volume & Issue: Volume 9, Issue 2

Page(s): 751 - 755
Article Preview & Download


Share This Article

Join our RMS

Conference Alert

NCSEM 2024

National Conference on Sustainable Engineering and Management - 2024

Last Date: 15th March 2024

Call For Paper

Volume 11 Issue 1

Last Date for paper submitting for Latest Issue is 25 June 2024

About Us

IJIRT.org enables door in research by providing high quality research articles in open access market.

Send us any query related to your research on editor@ijirt.org

Social Media

Google Verified Reviews