Visual Indexing of Large Scale Train-Borne Video for Rail Condition Perceiving

Peng DAI; Shengchun WANG; Yaping HUANG; Hao WANG; Xinyu DU; Qiang HAN

doi:10.1587/transinf.2016PCP0020

Visual Indexing of Large Scale Train-Borne Video for Rail Condition Perceiving

Peng DAI, Shengchun WANG, Yaping HUANG, Hao WANG, Xinyu DU, Qiang HAN

Full Text Views

0

Cite this

Summary :

Train-borne video captured from the camera installed in the front or back of the train has been used for railway environment surveillance, including missing communication units and bolts on the track, broken fences, unpredictable objects falling into the rail area or hanging on wires on the top of rails. Moreover, the track condition can be perceived visually from the video by observing and analyzing the train-swaying arising from the track irregularity. However, it's a time-consuming and labor-intensive work to examine the whole large scale video up to dozens of hours frequently. In this paper, we propose a simple and effective method to detect the train-swaying quickly and automatically. We first generate the long rail track panorama (RTP) by stitching the stripes cut from the video frames, and then extract track profile to perform the unevenness detection algorithm on the RTP. The experimental results show that RTP, the compact video representation, can fast examine the visual train-swaying information for track condition perceiving, on which we detect the irregular spots with 92.86% recall and 82.98% precision in only 2 minutes computation from the video close to 1 hour.

Publication: IEICE TRANSACTIONS on Information Vol.E100-D No.9 pp.2017-2026

Publication Date: 2017/09/01

Publicized: 2017/06/14

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2016PCP0020

Type of Manuscript: Special Section PAPER (Special Section on Picture Coding and Image Media Processing)

Category

Authors

Peng DAI
  China Academy of Railway Sciences
Shengchun WANG
  China Academy of Railway Sciences
Yaping HUANG
  Beijing Jiaotong University
Hao WANG
  China Academy of Railway Sciences
Xinyu DU
  China Academy of Railway Sciences
Qiang HAN
  China Academy of Railway Sciences

Keyword

route panorama, video indexing, train-borne video, train-swaying, track irregularity

Cite this

Copy

Peng DAI, Shengchun WANG, Yaping HUANG, Hao WANG, Xinyu DU, Qiang HAN, "Visual Indexing of Large Scale Train-Borne Video for Rail Condition Perceiving" in IEICE TRANSACTIONS on Information, vol. E100-D, no. 9, pp. 2017-2026, September 2017, doi: 10.1587/transinf.2016PCP0020.
Abstract: Train-borne video captured from the camera installed in the front or back of the train has been used for railway environment surveillance, including missing communication units and bolts on the track, broken fences, unpredictable objects falling into the rail area or hanging on wires on the top of rails. Moreover, the track condition can be perceived visually from the video by observing and analyzing the train-swaying arising from the track irregularity. However, it's a time-consuming and labor-intensive work to examine the whole large scale video up to dozens of hours frequently. In this paper, we propose a simple and effective method to detect the train-swaying quickly and automatically. We first generate the long rail track panorama (RTP) by stitching the stripes cut from the video frames, and then extract track profile to perform the unevenness detection algorithm on the RTP. The experimental results show that RTP, the compact video representation, can fast examine the visual train-swaying information for track condition perceiving, on which we detect the irregular spots with 92.86% recall and 82.98% precision in only 2 minutes computation from the video close to 1 hour.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2016PCP0020/_p

Copy

@ARTICLE{e100-d_9_2017,
author={Peng DAI, Shengchun WANG, Yaping HUANG, Hao WANG, Xinyu DU, Qiang HAN, },
journal={IEICE TRANSACTIONS on Information},
title={Visual Indexing of Large Scale Train-Borne Video for Rail Condition Perceiving},
year={2017},
volume={E100-D},
number={9},
pages={2017-2026},
abstract={Train-borne video captured from the camera installed in the front or back of the train has been used for railway environment surveillance, including missing communication units and bolts on the track, broken fences, unpredictable objects falling into the rail area or hanging on wires on the top of rails. Moreover, the track condition can be perceived visually from the video by observing and analyzing the train-swaying arising from the track irregularity. However, it's a time-consuming and labor-intensive work to examine the whole large scale video up to dozens of hours frequently. In this paper, we propose a simple and effective method to detect the train-swaying quickly and automatically. We first generate the long rail track panorama (RTP) by stitching the stripes cut from the video frames, and then extract track profile to perform the unevenness detection algorithm on the RTP. The experimental results show that RTP, the compact video representation, can fast examine the visual train-swaying information for track condition perceiving, on which we detect the irregular spots with 92.86% recall and 82.98% precision in only 2 minutes computation from the video close to 1 hour.},
keywords={},
doi={10.1587/transinf.2016PCP0020},
ISSN={1745-1361},
month={September},}

Copy

TY - JOUR
TI - Visual Indexing of Large Scale Train-Borne Video for Rail Condition Perceiving
T2 - IEICE TRANSACTIONS on Information
SP - 2017
EP - 2026
AU - Peng DAI
AU - Shengchun WANG
AU - Yaping HUANG
AU - Hao WANG
AU - Xinyu DU
AU - Qiang HAN
PY - 2017
DO - 10.1587/transinf.2016PCP0020
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E100-D
IS - 9
JA - IEICE TRANSACTIONS on Information
Y1 - September 2017
AB - Train-borne video captured from the camera installed in the front or back of the train has been used for railway environment surveillance, including missing communication units and bolts on the track, broken fences, unpredictable objects falling into the rail area or hanging on wires on the top of rails. Moreover, the track condition can be perceived visually from the video by observing and analyzing the train-swaying arising from the track irregularity. However, it's a time-consuming and labor-intensive work to examine the whole large scale video up to dozens of hours frequently. In this paper, we propose a simple and effective method to detect the train-swaying quickly and automatically. We first generate the long rail track panorama (RTP) by stitching the stripes cut from the video frames, and then extract track profile to perform the unevenness detection algorithm on the RTP. The experimental results show that RTP, the compact video representation, can fast examine the visual train-swaying information for track condition perceiving, on which we detect the irregular spots with 92.86% recall and 82.98% precision in only 2 minutes computation from the video close to 1 hour.
ER -