Wheelchair detection using cascaded decision tree

Chun Rong Huang, Pau-Choo Chung, Kuo Wei Lin, Sheng Chieh Tseng

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

One of the major goals of healthcare systems is to automatically monitor patients of special needs and alarm the caregivers for providing assistant. In this paper, an efficient single-camera multidirectional wheelchair detector based on a cascaded decision tree (CDT) is proposed to detect a wheelchair and its moving direction simultaneously from video frames for a healthcare system. Our approach combines a decision tree structure and boosted-cascade classifiers to construct a new CDT that can perform early confidence decisions in a hierarchical manner to rapidly reject nonwheelchairs and decide the moving directions. We also impose the tracking history to guide detection routes in the CDT to further reduce detection time and increase detection accuracy. The experiments show over 92% detection rate under cluttered scenes.

Original languageEnglish
Article number5353620
Pages (from-to)292-300
Number of pages9
JournalIEEE Transactions on Information Technology in Biomedicine
Volume14
Issue number2
DOIs
Publication statusPublished - 2010 Mar 1

Fingerprint

Decision Trees
Wheelchairs
Decision trees
Delivery of Health Care
Caregivers
Classifiers
History
Cameras
Detectors
Experiments
Direction compound

All Science Journal Classification (ASJC) codes

  • Biotechnology
  • Computer Science Applications
  • Electrical and Electronic Engineering

Cite this

Huang, Chun Rong ; Chung, Pau-Choo ; Lin, Kuo Wei ; Tseng, Sheng Chieh. / Wheelchair detection using cascaded decision tree. In: IEEE Transactions on Information Technology in Biomedicine. 2010 ; Vol. 14, No. 2. pp. 292-300.
@article{f84d357b4d674a6bac38e30523d5cbfd,
title = "Wheelchair detection using cascaded decision tree",
abstract = "One of the major goals of healthcare systems is to automatically monitor patients of special needs and alarm the caregivers for providing assistant. In this paper, an efficient single-camera multidirectional wheelchair detector based on a cascaded decision tree (CDT) is proposed to detect a wheelchair and its moving direction simultaneously from video frames for a healthcare system. Our approach combines a decision tree structure and boosted-cascade classifiers to construct a new CDT that can perform early confidence decisions in a hierarchical manner to rapidly reject nonwheelchairs and decide the moving directions. We also impose the tracking history to guide detection routes in the CDT to further reduce detection time and increase detection accuracy. The experiments show over 92{\%} detection rate under cluttered scenes.",
author = "Huang, {Chun Rong} and Pau-Choo Chung and Lin, {Kuo Wei} and Tseng, {Sheng Chieh}",
year = "2010",
month = "3",
day = "1",
doi = "10.1109/TITB.2009.2037618",
language = "English",
volume = "14",
pages = "292--300",
journal = "IEEE Journal of Biomedical and Health Informatics",
issn = "2168-2194",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "2",

}

Wheelchair detection using cascaded decision tree. / Huang, Chun Rong; Chung, Pau-Choo; Lin, Kuo Wei; Tseng, Sheng Chieh.

In: IEEE Transactions on Information Technology in Biomedicine, Vol. 14, No. 2, 5353620, 01.03.2010, p. 292-300.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Wheelchair detection using cascaded decision tree

AU - Huang, Chun Rong

AU - Chung, Pau-Choo

AU - Lin, Kuo Wei

AU - Tseng, Sheng Chieh

PY - 2010/3/1

Y1 - 2010/3/1

N2 - One of the major goals of healthcare systems is to automatically monitor patients of special needs and alarm the caregivers for providing assistant. In this paper, an efficient single-camera multidirectional wheelchair detector based on a cascaded decision tree (CDT) is proposed to detect a wheelchair and its moving direction simultaneously from video frames for a healthcare system. Our approach combines a decision tree structure and boosted-cascade classifiers to construct a new CDT that can perform early confidence decisions in a hierarchical manner to rapidly reject nonwheelchairs and decide the moving directions. We also impose the tracking history to guide detection routes in the CDT to further reduce detection time and increase detection accuracy. The experiments show over 92% detection rate under cluttered scenes.

AB - One of the major goals of healthcare systems is to automatically monitor patients of special needs and alarm the caregivers for providing assistant. In this paper, an efficient single-camera multidirectional wheelchair detector based on a cascaded decision tree (CDT) is proposed to detect a wheelchair and its moving direction simultaneously from video frames for a healthcare system. Our approach combines a decision tree structure and boosted-cascade classifiers to construct a new CDT that can perform early confidence decisions in a hierarchical manner to rapidly reject nonwheelchairs and decide the moving directions. We also impose the tracking history to guide detection routes in the CDT to further reduce detection time and increase detection accuracy. The experiments show over 92% detection rate under cluttered scenes.

UR - http://www.scopus.com/inward/record.url?scp=77949729422&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77949729422&partnerID=8YFLogxK

U2 - 10.1109/TITB.2009.2037618

DO - 10.1109/TITB.2009.2037618

M3 - Article

VL - 14

SP - 292

EP - 300

JO - IEEE Journal of Biomedical and Health Informatics

JF - IEEE Journal of Biomedical and Health Informatics

SN - 2168-2194

IS - 2

M1 - 5353620

ER -