Detection of sudden pedestrian crossings for driving assistance systems

In this paper, we study the problem of detecting sudden pedestrian crossings to assist drivers in avoiding accidents. This application has two major requirements: to detect crossing pedestrians as early as possible just as they enter the view of the car-mounted camera and to maintain a false alarm r...

Full description

Bibliographic Details
Main Authors: Han, Tony X., Xu, Yanwu, Xu, Dong, Lin, Stephen, Cao, Xianbin, Li, Xuelong
Other Authors: School of Computer Engineering
Format: Journal Article
Language:English
Published: 2013
Subjects:
Online Access:https://hdl.handle.net/10356/97129
http://hdl.handle.net/10220/11446
_version_ 1826116710315327488
author Han, Tony X.
Xu, Yanwu
Xu, Dong
Lin, Stephen
Cao, Xianbin
Li, Xuelong
author2 School of Computer Engineering
author_facet School of Computer Engineering
Han, Tony X.
Xu, Yanwu
Xu, Dong
Lin, Stephen
Cao, Xianbin
Li, Xuelong
author_sort Han, Tony X.
collection NTU
description In this paper, we study the problem of detecting sudden pedestrian crossings to assist drivers in avoiding accidents. This application has two major requirements: to detect crossing pedestrians as early as possible just as they enter the view of the car-mounted camera and to maintain a false alarm rate as low as possible for practical purposes. Although many current sliding-window-based approaches using various features and classification algorithms have been proposed for image-/video-based pedestrian detection, their performance in terms of accuracy and processing speed falls far short of practical application requirements. To address this problem, we propose a three-level coarse-to-fine video-based framework that detects partially visible pedestrians just as they enter the camera view, with low false alarm rate and high speed. The framework is tested on a new collection of high-resolution videos captured from a moving vehicle and yields a performance better than that of state-of-the-art pedestrian detection while running at a frame rate of 55 fps.
first_indexed 2024-10-01T04:16:09Z
format Journal Article
id ntu-10356/97129
institution Nanyang Technological University
language English
last_indexed 2024-10-01T04:16:09Z
publishDate 2013
record_format dspace
spelling ntu-10356/971292020-05-28T07:17:30Z Detection of sudden pedestrian crossings for driving assistance systems Han, Tony X. Xu, Yanwu Xu, Dong Lin, Stephen Cao, Xianbin Li, Xuelong School of Computer Engineering DRNTU::Engineering::Electrical and electronic engineering In this paper, we study the problem of detecting sudden pedestrian crossings to assist drivers in avoiding accidents. This application has two major requirements: to detect crossing pedestrians as early as possible just as they enter the view of the car-mounted camera and to maintain a false alarm rate as low as possible for practical purposes. Although many current sliding-window-based approaches using various features and classification algorithms have been proposed for image-/video-based pedestrian detection, their performance in terms of accuracy and processing speed falls far short of practical application requirements. To address this problem, we propose a three-level coarse-to-fine video-based framework that detects partially visible pedestrians just as they enter the camera view, with low false alarm rate and high speed. The framework is tested on a new collection of high-resolution videos captured from a moving vehicle and yields a performance better than that of state-of-the-art pedestrian detection while running at a frame rate of 55 fps. 2013-07-15T07:34:14Z 2019-12-06T19:39:13Z 2013-07-15T07:34:14Z 2019-12-06T19:39:13Z 2011 2011 Journal Article Xu, Y., Xu, D., Lin, S., Han, T. X., Cao, X., & Li, X. (2012). Detection of Sudden Pedestrian Crossings for Driving Assistance Systems. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 42(3), 729-739. 1083-4419 https://hdl.handle.net/10356/97129 http://hdl.handle.net/10220/11446 10.1109/TSMCB.2011.2175726 en IEEE transactions on systems, man, and cybernetics, part b (cybernetics) © 2011 IEEE.
spellingShingle DRNTU::Engineering::Electrical and electronic engineering
Han, Tony X.
Xu, Yanwu
Xu, Dong
Lin, Stephen
Cao, Xianbin
Li, Xuelong
Detection of sudden pedestrian crossings for driving assistance systems
title Detection of sudden pedestrian crossings for driving assistance systems
title_full Detection of sudden pedestrian crossings for driving assistance systems
title_fullStr Detection of sudden pedestrian crossings for driving assistance systems
title_full_unstemmed Detection of sudden pedestrian crossings for driving assistance systems
title_short Detection of sudden pedestrian crossings for driving assistance systems
title_sort detection of sudden pedestrian crossings for driving assistance systems
topic DRNTU::Engineering::Electrical and electronic engineering
url https://hdl.handle.net/10356/97129
http://hdl.handle.net/10220/11446
work_keys_str_mv AT hantonyx detectionofsuddenpedestriancrossingsfordrivingassistancesystems
AT xuyanwu detectionofsuddenpedestriancrossingsfordrivingassistancesystems
AT xudong detectionofsuddenpedestriancrossingsfordrivingassistancesystems
AT linstephen detectionofsuddenpedestriancrossingsfordrivingassistancesystems
AT caoxianbin detectionofsuddenpedestriancrossingsfordrivingassistancesystems
AT lixuelong detectionofsuddenpedestriancrossingsfordrivingassistancesystems