Deep Learning Framework for Pedestrian Collision Avoidance System (PeCAS)

11/11/2018
by   Peetak Mitra, et al.
0

Drowsy driving is a major cause of on-road accidents in the US, which sometimes is fatal to unsuspecting pedestrians. This framework based on Deep Learning proposes an approach to detect the onset of drowsiness in a vehicle operator especially alerting the driver when in the proximity of a pedestrian. Using Convolutional Neural Network (CNN), an approach is proposed to detect drowsiness based on the Viola-Jones algorithm. The pedestrian detector is also based on a deep CNN architecture and is capable to detect multiple pedestrians. In the end, an integration of the output from the two architectures is fed into an Arduino hardware kit to generate warnings for the vehicle operator.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 2

07/02/2019

Vision-based Pedestrian Alert Safety System (PASS) for Signalized Intersections

Although Vehicle-to-Pedestrian (V2P) communication can significantly imp...
12/20/2016

End-to-End Pedestrian Collision Warning System based on a Convolutional Neural Network with Semantic Segmentation

Traditional pedestrian collision warning systems sometimes raise alarms ...
09/24/2019

Monocular Pedestrian Orientation Estimation Based on Deep 2D-3D Feedforward

Accurate pedestrian orientation estimation of autonomous driving helps t...
02/06/2018

Utility Decomposition with Deep Corrections for Scalable Planning under Uncertainty

Decomposition methods have been proposed in the past to approximate solu...
04/13/2021

What is the appropriate speed for an autonomous vehicle? Designing a Pedestrian Aware Contextual Speed Controller

Social acceptance is a major hurdle for autonomous vehicle technology, c...
09/08/2016

Reduced Memory Region Based Deep Convolutional Neural Network Detection

Accurate pedestrian detection has a primary role in automotive safety: f...
04/20/2018

Enabling WiFi P2P-Based Pedestrian Safety App

Recent studies reported a significant increase in the number of accident...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.