Robust Pedestrian Tracking and Recognition from FLIR Video: A Unified Approach via Sparse Coding
Sparse coding is an emerging method that has been successfully applied to both robust object tracking and recognition in the vision literature. In this paper, we propose to explore a sparse coding-based approach toward joint object tracking-and-recognition and explore its potential in the analysis o...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2014-06-01
|
Series: | Sensors |
Subjects: | |
Online Access: | http://www.mdpi.com/1424-8220/14/6/11245 |
id |
doaj-a3ecfe99abbb4f5ea8b5e8cf851b78db |
---|---|
record_format |
Article |
spelling |
doaj-a3ecfe99abbb4f5ea8b5e8cf851b78db2020-11-25T00:54:37ZengMDPI AGSensors1424-82202014-06-01146112451125910.3390/s140611245s140611245Robust Pedestrian Tracking and Recognition from FLIR Video: A Unified Approach via Sparse CodingXin Li0Rui Guo1Chao Chen2Lane Department of CSEE, Morgantown, WV 26506-6109, USADepartment of EECS, University of Tennessee, Knoxville, TN 37996, USADepartment of Electrical and Computer Engineering, University of Missouri, Columbia, MO 65211, USASparse coding is an emerging method that has been successfully applied to both robust object tracking and recognition in the vision literature. In this paper, we propose to explore a sparse coding-based approach toward joint object tracking-and-recognition and explore its potential in the analysis of forward-looking infrared (FLIR) video to support nighttime machine vision systems. A key technical contribution of this work is to unify existing sparse coding-based approaches toward tracking and recognition under the same framework, so that they can benefit from each other in a closed-loop. On the one hand, tracking the same object through temporal frames allows us to achieve improved recognition performance through dynamical updating of template/dictionary and combining multiple recognition results; on the other hand, the recognition of individual objects facilitates the tracking of multiple objects (i.e., walking pedestrians), especially in the presence of occlusion within a crowded environment. We report experimental results on both the CASIAPedestrian Database and our own collected FLIR video database to demonstrate the effectiveness of the proposed joint tracking-and-recognition approach.http://www.mdpi.com/1424-8220/14/6/11245robust trackingpedestrian recognitionsparse codingtemplate updatingFLIR video |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Xin Li Rui Guo Chao Chen |
spellingShingle |
Xin Li Rui Guo Chao Chen Robust Pedestrian Tracking and Recognition from FLIR Video: A Unified Approach via Sparse Coding Sensors robust tracking pedestrian recognition sparse coding template updating FLIR video |
author_facet |
Xin Li Rui Guo Chao Chen |
author_sort |
Xin Li |
title |
Robust Pedestrian Tracking and Recognition from FLIR Video: A Unified Approach via Sparse Coding |
title_short |
Robust Pedestrian Tracking and Recognition from FLIR Video: A Unified Approach via Sparse Coding |
title_full |
Robust Pedestrian Tracking and Recognition from FLIR Video: A Unified Approach via Sparse Coding |
title_fullStr |
Robust Pedestrian Tracking and Recognition from FLIR Video: A Unified Approach via Sparse Coding |
title_full_unstemmed |
Robust Pedestrian Tracking and Recognition from FLIR Video: A Unified Approach via Sparse Coding |
title_sort |
robust pedestrian tracking and recognition from flir video: a unified approach via sparse coding |
publisher |
MDPI AG |
series |
Sensors |
issn |
1424-8220 |
publishDate |
2014-06-01 |
description |
Sparse coding is an emerging method that has been successfully applied to both robust object tracking and recognition in the vision literature. In this paper, we propose to explore a sparse coding-based approach toward joint object tracking-and-recognition and explore its potential in the analysis of forward-looking infrared (FLIR) video to support nighttime machine vision systems. A key technical contribution of this work is to unify existing sparse coding-based approaches toward tracking and recognition under the same framework, so that they can benefit from each other in a closed-loop. On the one hand, tracking the same object through temporal frames allows us to achieve improved recognition performance through dynamical updating of template/dictionary and combining multiple recognition results; on the other hand, the recognition of individual objects facilitates the tracking of multiple objects (i.e., walking pedestrians), especially in the presence of occlusion within a crowded environment. We report experimental results on both the CASIAPedestrian Database and our own collected FLIR video database to demonstrate the effectiveness of the proposed joint tracking-and-recognition approach. |
topic |
robust tracking pedestrian recognition sparse coding template updating FLIR video |
url |
http://www.mdpi.com/1424-8220/14/6/11245 |
work_keys_str_mv |
AT xinli robustpedestriantrackingandrecognitionfromflirvideoaunifiedapproachviasparsecoding AT ruiguo robustpedestriantrackingandrecognitionfromflirvideoaunifiedapproachviasparsecoding AT chaochen robustpedestriantrackingandrecognitionfromflirvideoaunifiedapproachviasparsecoding |
_version_ |
1725233530163691520 |