Rapid and robust background modeling technique for low-cost road traffic surveillance systems
Fast and accurate detection of vehicles on road traffic scenes captured by traffic surveillance cameras, is essential for large-scale deployment of automated traffic surveillance systems. The state-of-the-art techniques typically employ background modeling for low-complexity foreground detection. Ho...
Saved in:
Main Authors: | , , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
2021
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/147723 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-147723 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1477232021-04-12T09:21:54Z Rapid and robust background modeling technique for low-cost road traffic surveillance systems Garg, Kratika Ramakrishnan, Nirmala Prakash, Alok Srikanthan, Thambipillai School of Computer Science and Engineering Engineering::Computer science and engineering Intelligent Transport Systems Adaptation Models Fast and accurate detection of vehicles on road traffic scenes captured by traffic surveillance cameras, is essential for large-scale deployment of automated traffic surveillance systems. The state-of-the-art techniques typically employ background modeling for low-complexity foreground detection. However, this is a challenging problem as these methods need to be robust to varying road scene conditions (such as illumination changes, camera jitter, stationary vehicles, and heavy traffic) leading to huge computation cost. In this paper, we propose a highly accurate yet low-complexity foreground (i.e., vehicle) detection technique, which can effectively deal with the varying road scene conditions, and generate accurate pixel-level foreground masks in real-time. We propose a novel robust block-based feature suitable for modeling road background and detecting vehicles as foreground, and employ Bayesian probabilistic modeling on these features. The experimental evaluations on widely used traffic datasets demonstrate that the proposed method can achieve comparable accuracy to the existing state-of-the-art techniques but at a much higher processing frame rate (40x speedup over PAWCS). The real-time performance of the proposed system has also been demonstrated by implementing it on a low-cost embedded platform, Odroid XU-4, that still achieves a frame rate of over 80 frames/s, thereby enabling the real-time detection of foreground objects in road scenes. 2021-04-12T09:21:54Z 2021-04-12T09:21:54Z 2020 Journal Article Garg, K., Ramakrishnan, N., Prakash, A. & Srikanthan, T. (2020). Rapid and robust background modeling technique for low-cost road traffic surveillance systems. IEEE Transactions On Intelligent Transportation Systems, 21(5), 2204-2215. https://dx.doi.org/10.1109/TITS.2019.2917560 1558-0016 0000-0003-3937-4395 0000-0001-8257-2974 https://hdl.handle.net/10356/147723 10.1109/TITS.2019.2917560 2-s2.0-85084472097 5 21 2204 2215 en NRF TUMCREATE IEEE Transactions on Intelligent Transportation Systems © 2020 Institute of Electrical and Electronics Engineers (IEEE). All rights reserved. |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Engineering::Computer science and engineering Intelligent Transport Systems Adaptation Models |
spellingShingle |
Engineering::Computer science and engineering Intelligent Transport Systems Adaptation Models Garg, Kratika Ramakrishnan, Nirmala Prakash, Alok Srikanthan, Thambipillai Rapid and robust background modeling technique for low-cost road traffic surveillance systems |
description |
Fast and accurate detection of vehicles on road traffic scenes captured by traffic surveillance cameras, is essential for large-scale deployment of automated traffic surveillance systems. The state-of-the-art techniques typically employ background modeling for low-complexity foreground detection. However, this is a challenging problem as these methods need to be robust to varying road scene conditions (such as illumination changes, camera jitter, stationary vehicles, and heavy traffic) leading to huge computation cost. In this paper, we propose a highly accurate yet low-complexity foreground (i.e., vehicle) detection technique, which can effectively deal with the varying road scene conditions, and generate accurate pixel-level foreground masks in real-time. We propose a novel robust block-based feature suitable for modeling road background and detecting vehicles as foreground, and employ Bayesian probabilistic modeling on these features. The experimental evaluations on widely used traffic datasets demonstrate that the proposed method can achieve comparable accuracy to the existing state-of-the-art techniques but at a much higher processing frame rate (40x speedup over PAWCS). The real-time performance of the proposed system has also been demonstrated by implementing it on a low-cost embedded platform, Odroid XU-4, that still achieves a frame rate of over 80 frames/s, thereby enabling the real-time detection of foreground objects in road scenes. |
author2 |
School of Computer Science and Engineering |
author_facet |
School of Computer Science and Engineering Garg, Kratika Ramakrishnan, Nirmala Prakash, Alok Srikanthan, Thambipillai |
format |
Article |
author |
Garg, Kratika Ramakrishnan, Nirmala Prakash, Alok Srikanthan, Thambipillai |
author_sort |
Garg, Kratika |
title |
Rapid and robust background modeling technique for low-cost road traffic surveillance systems |
title_short |
Rapid and robust background modeling technique for low-cost road traffic surveillance systems |
title_full |
Rapid and robust background modeling technique for low-cost road traffic surveillance systems |
title_fullStr |
Rapid and robust background modeling technique for low-cost road traffic surveillance systems |
title_full_unstemmed |
Rapid and robust background modeling technique for low-cost road traffic surveillance systems |
title_sort |
rapid and robust background modeling technique for low-cost road traffic surveillance systems |
publishDate |
2021 |
url |
https://hdl.handle.net/10356/147723 |
_version_ |
1696984389080055808 |