Precise Segmentation and Estimation of Pedestrian Trajectory Using On-Board Monocular Cameras

HyungKwan KIM; Yuuki SHIBAYAMA; Shunsuke KAMIJO

doi:10.1587/transfun.E95.A.296

Precise Segmentation and Estimation of Pedestrian Trajectory Using On-Board Monocular Cameras

HyungKwan KIM, Yuuki SHIBAYAMA, Shunsuke KAMIJO

Full Text Views

0

Cite this

Summary :

This paper presents a general algorithm for pedestrian detection by on-board monocular camera which can be applied to cameras of various view ranges. Under the assumption that motion of background can be nearly approximated as a linear function, the Spatio-Temporal MRF (S-T MRF) model segments foreground objects. The foreground objects contain both pedestrian and non-pedestrian urban objects, verification was conducted by a cascaded classifier. However, the segmentation results based on motion were not exactly fit into pedestrian on the image so that shrunk or inflated pedestrian were generated. This causes errors on extracting pedestrian trajectory. For precise positioning, we implemented two types of feedback algorithm for ROI correction using the Kalman filter and the voting result of Motion-classifier and HOG-classifier. We confirmed that those ROI Corrections successfully extract precise area of pedestrian and decrease the false negative rate. Elaborately extracted pedestrian trajectory could be used as a useful source for predicting collision to pedestrian.

Publication: IEICE TRANSACTIONS on Fundamentals Vol.E95-A No.1 pp.296-304

Publication Date: 2012/01/01

Publicized

Online ISSN: 1745-1337

DOI: 10.1587/transfun.E95.A.296

Type of Manuscript: Special Section PAPER (Special Section on Intelligent Transport Systems)

Category: ITS

Cite this

Copy

HyungKwan KIM, Yuuki SHIBAYAMA, Shunsuke KAMIJO, "Precise Segmentation and Estimation of Pedestrian Trajectory Using On-Board Monocular Cameras" in IEICE TRANSACTIONS on Fundamentals, vol. E95-A, no. 1, pp. 296-304, January 2012, doi: 10.1587/transfun.E95.A.296.
Abstract: This paper presents a general algorithm for pedestrian detection by on-board monocular camera which can be applied to cameras of various view ranges. Under the assumption that motion of background can be nearly approximated as a linear function, the Spatio-Temporal MRF (S-T MRF) model segments foreground objects. The foreground objects contain both pedestrian and non-pedestrian urban objects, verification was conducted by a cascaded classifier. However, the segmentation results based on motion were not exactly fit into pedestrian on the image so that shrunk or inflated pedestrian were generated. This causes errors on extracting pedestrian trajectory. For precise positioning, we implemented two types of feedback algorithm for ROI correction using the Kalman filter and the voting result of Motion-classifier and HOG-classifier. We confirmed that those ROI Corrections successfully extract precise area of pedestrian and decrease the false negative rate. Elaborately extracted pedestrian trajectory could be used as a useful source for predicting collision to pedestrian.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.E95.A.296/_p

Copy

@ARTICLE{e95-a_1_296,
author={HyungKwan KIM, Yuuki SHIBAYAMA, Shunsuke KAMIJO, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Precise Segmentation and Estimation of Pedestrian Trajectory Using On-Board Monocular Cameras},
year={2012},
volume={E95-A},
number={1},
pages={296-304},
abstract={This paper presents a general algorithm for pedestrian detection by on-board monocular camera which can be applied to cameras of various view ranges. Under the assumption that motion of background can be nearly approximated as a linear function, the Spatio-Temporal MRF (S-T MRF) model segments foreground objects. The foreground objects contain both pedestrian and non-pedestrian urban objects, verification was conducted by a cascaded classifier. However, the segmentation results based on motion were not exactly fit into pedestrian on the image so that shrunk or inflated pedestrian were generated. This causes errors on extracting pedestrian trajectory. For precise positioning, we implemented two types of feedback algorithm for ROI correction using the Kalman filter and the voting result of Motion-classifier and HOG-classifier. We confirmed that those ROI Corrections successfully extract precise area of pedestrian and decrease the false negative rate. Elaborately extracted pedestrian trajectory could be used as a useful source for predicting collision to pedestrian.},
keywords={},
doi={10.1587/transfun.E95.A.296},
ISSN={1745-1337},
month={January},}

Copy

TY - JOUR
TI - Precise Segmentation and Estimation of Pedestrian Trajectory Using On-Board Monocular Cameras
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 296
EP - 304
AU - HyungKwan KIM
AU - Yuuki SHIBAYAMA
AU - Shunsuke KAMIJO
PY - 2012
DO - 10.1587/transfun.E95.A.296
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E95-A
IS - 1
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - January 2012
AB - This paper presents a general algorithm for pedestrian detection by on-board monocular camera which can be applied to cameras of various view ranges. Under the assumption that motion of background can be nearly approximated as a linear function, the Spatio-Temporal MRF (S-T MRF) model segments foreground objects. The foreground objects contain both pedestrian and non-pedestrian urban objects, verification was conducted by a cascaded classifier. However, the segmentation results based on motion were not exactly fit into pedestrian on the image so that shrunk or inflated pedestrian were generated. This causes errors on extracting pedestrian trajectory. For precise positioning, we implemented two types of feedback algorithm for ROI correction using the Kalman filter and the voting result of Motion-classifier and HOG-classifier. We confirmed that those ROI Corrections successfully extract precise area of pedestrian and decrease the false negative rate. Elaborately extracted pedestrian trajectory could be used as a useful source for predicting collision to pedestrian.
ER -