End-to-end pedestrian collision warning system based on a convolutional neural network with semantic segmentation

Heechul Jung, Min Kook Choi, Kwon Soon, Woo Young Jung

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

8 Scopus citations

Abstract

Traditional pedestrian collision warning systems sometimes raise alarms even when there is no danger (e.g., when all pedestrians are walking on the sidewalk). These false alarms can make it difficult for drivers to concentrate on their driving. In this paper, we propose a novel framework for an end-to-end pedestrian collision warning system based on a convolutional neural network. Semantic segmentation information is used to train the convolutional neural network and two loss functions, such as cross entropy and Euclidean losses, are minimized. Finally, we demonstrate the effectiveness of our method in reducing false alarms and increasing warning accuracy compared to a traditional histogram of oriented gradients (HOG)-based system.

Original languageEnglish
Title of host publication2018 IEEE International Conference on Consumer Electronics, ICCE 2018
EditorsSaraju P. Mohanty, Peter Corcoran, Hai Li, Anirban Sengupta, Jong-Hyouk Lee
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-3
Number of pages3
ISBN (Electronic)9781538630259
DOIs
StatePublished - 26 Mar 2018
Event2018 IEEE International Conference on Consumer Electronics, ICCE 2018 - Las Vegas, United States
Duration: 12 Jan 201814 Jan 2018

Publication series

Name2018 IEEE International Conference on Consumer Electronics, ICCE 2018
Volume2018-January

Conference

Conference2018 IEEE International Conference on Consumer Electronics, ICCE 2018
Country/TerritoryUnited States
CityLas Vegas
Period12/01/1814/01/18

Fingerprint

Dive into the research topics of 'End-to-end pedestrian collision warning system based on a convolutional neural network with semantic segmentation'. Together they form a unique fingerprint.

Cite this