Video stabilization for a camcorder mounted on a moving vehicle

Yu Ming Liang, Hsiao Rong Tyan, Shyang Lih Chang, Hong Yuan Mark Liao, Sei-Wang Chen

Research output: Contribution to journalArticle

70 Citations (Scopus)

Abstract

Vision systems play an important role in many intelligent transportation systems (ITS) applications, such as traffic monitoring, traffic law reinforcement, driver assistance, and automatic vehicle guidance. These systems installed in either outdoor environments or vehicles have often suffered from image instability. In this paper, a video stabilization technique for a camcorder mounted on a moving vehicle is presented. The proposed approach takes full advantage of the a priori information of traffic images, significantly reducing the computational and time complexities. There are four major steps involved in the proposed approach: global feature extraction, camcorder motion estimation, motion taxonomy, and image compensation. We begin with extracting the global features of lane lines and the road vanishing point from the input image. The extracted features are then combined with those detected in previous images to compute the camcorder motion corresponding to the current input image. The computed motion consists of both expected and unexpected components. They are discriminated and the expected motion component is further smoothed. The resulting motion is next integrated with a predicted motion, which is extrapolated from the previous desired camcorder motions, leading to the desired camcorder motion associated with the input image under consideration. The current input image is finally stabilized based on the computed desired camcorder motion using an image transformation technique. A series of experiments with both real and synthetic data have been conducted. The experimental results have revealed the effectiveness of the proposed technique.

Original languageEnglish
Pages (from-to)1636-1648
Number of pages13
JournalIEEE Transactions on Vehicular Technology
Volume53
Issue number6
DOIs
Publication statusPublished - 2004 Nov 1

Fingerprint

Stabilization
Motion
Motion estimation
Taxonomies
Feature extraction
Reinforcement
Traffic
Monitoring
Image Transformation
Intelligent Transportation Systems
Driver Assistance
Experiments
Motion Estimation
Vision System
Synthetic Data
Taxonomy
Feature Extraction
Time Complexity
Guidance
Computational Complexity

Keywords

  • Image compensation
  • In-vehicle vision systems
  • Intelligent transportation systems (ITS)
  • Motion estimation
  • Motion taxonomy
  • Video stabilization

ASJC Scopus subject areas

  • Automotive Engineering
  • Aerospace Engineering
  • Applied Mathematics
  • Electrical and Electronic Engineering

Cite this

Video stabilization for a camcorder mounted on a moving vehicle. / Liang, Yu Ming; Tyan, Hsiao Rong; Chang, Shyang Lih; Liao, Hong Yuan Mark; Chen, Sei-Wang.

In: IEEE Transactions on Vehicular Technology, Vol. 53, No. 6, 01.11.2004, p. 1636-1648.

Research output: Contribution to journalArticle

Liang, Yu Ming ; Tyan, Hsiao Rong ; Chang, Shyang Lih ; Liao, Hong Yuan Mark ; Chen, Sei-Wang. / Video stabilization for a camcorder mounted on a moving vehicle. In: IEEE Transactions on Vehicular Technology. 2004 ; Vol. 53, No. 6. pp. 1636-1648.
@article{6aecf51d562d488e991c144f053f1a5d,
title = "Video stabilization for a camcorder mounted on a moving vehicle",
abstract = "Vision systems play an important role in many intelligent transportation systems (ITS) applications, such as traffic monitoring, traffic law reinforcement, driver assistance, and automatic vehicle guidance. These systems installed in either outdoor environments or vehicles have often suffered from image instability. In this paper, a video stabilization technique for a camcorder mounted on a moving vehicle is presented. The proposed approach takes full advantage of the a priori information of traffic images, significantly reducing the computational and time complexities. There are four major steps involved in the proposed approach: global feature extraction, camcorder motion estimation, motion taxonomy, and image compensation. We begin with extracting the global features of lane lines and the road vanishing point from the input image. The extracted features are then combined with those detected in previous images to compute the camcorder motion corresponding to the current input image. The computed motion consists of both expected and unexpected components. They are discriminated and the expected motion component is further smoothed. The resulting motion is next integrated with a predicted motion, which is extrapolated from the previous desired camcorder motions, leading to the desired camcorder motion associated with the input image under consideration. The current input image is finally stabilized based on the computed desired camcorder motion using an image transformation technique. A series of experiments with both real and synthetic data have been conducted. The experimental results have revealed the effectiveness of the proposed technique.",
keywords = "Image compensation, In-vehicle vision systems, Intelligent transportation systems (ITS), Motion estimation, Motion taxonomy, Video stabilization",
author = "Liang, {Yu Ming} and Tyan, {Hsiao Rong} and Chang, {Shyang Lih} and Liao, {Hong Yuan Mark} and Sei-Wang Chen",
year = "2004",
month = "11",
day = "1",
doi = "10.1109/TVT.2004.836923",
language = "English",
volume = "53",
pages = "1636--1648",
journal = "IEEE Transactions on Vehicular Technology",
issn = "0018-9545",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "6",

}

TY - JOUR

T1 - Video stabilization for a camcorder mounted on a moving vehicle

AU - Liang, Yu Ming

AU - Tyan, Hsiao Rong

AU - Chang, Shyang Lih

AU - Liao, Hong Yuan Mark

AU - Chen, Sei-Wang

PY - 2004/11/1

Y1 - 2004/11/1

N2 - Vision systems play an important role in many intelligent transportation systems (ITS) applications, such as traffic monitoring, traffic law reinforcement, driver assistance, and automatic vehicle guidance. These systems installed in either outdoor environments or vehicles have often suffered from image instability. In this paper, a video stabilization technique for a camcorder mounted on a moving vehicle is presented. The proposed approach takes full advantage of the a priori information of traffic images, significantly reducing the computational and time complexities. There are four major steps involved in the proposed approach: global feature extraction, camcorder motion estimation, motion taxonomy, and image compensation. We begin with extracting the global features of lane lines and the road vanishing point from the input image. The extracted features are then combined with those detected in previous images to compute the camcorder motion corresponding to the current input image. The computed motion consists of both expected and unexpected components. They are discriminated and the expected motion component is further smoothed. The resulting motion is next integrated with a predicted motion, which is extrapolated from the previous desired camcorder motions, leading to the desired camcorder motion associated with the input image under consideration. The current input image is finally stabilized based on the computed desired camcorder motion using an image transformation technique. A series of experiments with both real and synthetic data have been conducted. The experimental results have revealed the effectiveness of the proposed technique.

AB - Vision systems play an important role in many intelligent transportation systems (ITS) applications, such as traffic monitoring, traffic law reinforcement, driver assistance, and automatic vehicle guidance. These systems installed in either outdoor environments or vehicles have often suffered from image instability. In this paper, a video stabilization technique for a camcorder mounted on a moving vehicle is presented. The proposed approach takes full advantage of the a priori information of traffic images, significantly reducing the computational and time complexities. There are four major steps involved in the proposed approach: global feature extraction, camcorder motion estimation, motion taxonomy, and image compensation. We begin with extracting the global features of lane lines and the road vanishing point from the input image. The extracted features are then combined with those detected in previous images to compute the camcorder motion corresponding to the current input image. The computed motion consists of both expected and unexpected components. They are discriminated and the expected motion component is further smoothed. The resulting motion is next integrated with a predicted motion, which is extrapolated from the previous desired camcorder motions, leading to the desired camcorder motion associated with the input image under consideration. The current input image is finally stabilized based on the computed desired camcorder motion using an image transformation technique. A series of experiments with both real and synthetic data have been conducted. The experimental results have revealed the effectiveness of the proposed technique.

KW - Image compensation

KW - In-vehicle vision systems

KW - Intelligent transportation systems (ITS)

KW - Motion estimation

KW - Motion taxonomy

KW - Video stabilization

UR - http://www.scopus.com/inward/record.url?scp=10244251590&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=10244251590&partnerID=8YFLogxK

U2 - 10.1109/TVT.2004.836923

DO - 10.1109/TVT.2004.836923

M3 - Article

VL - 53

SP - 1636

EP - 1648

JO - IEEE Transactions on Vehicular Technology

JF - IEEE Transactions on Vehicular Technology

SN - 0018-9545

IS - 6

ER -