Matching vehicles using hubert scanning distance

Tian Li, Seiichiro Kamata, Kazuyuki Tsuneyoshi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Matching objects is a fundamental problem for any object detection system. Feature-based methods in matching objects such as vehicles often encounter the problem of correspondences between features of two related patterns. The features may be points, lines, curves and regions. Point pattern matching (PPM) is a primary and essential approach for establishing a correspondence within two related patterns. Although some well-known Hausdorff distance measures work well for this task, they are very computational expensive and suffer from the noise of images. In this paper, we propose a novel similarity measure using Hilbert curve named Hilbert scanning distance (HSD) to resolve the problems. This method computes the distance measure in one-dimensional (1-D) sequence in stead of in two-dimensional (2-D) image space, which greatly reduce the computational complexity. By applying a threshold elimination function, extreme distances caused by noise and position errors (e.g. those that occur with feature or edge extraction) are removed. The experimental results show that HSD can provide sufficient information for matching -vehicles within low computational complexity. We believe this point out a new direction for the research of PPM.

Original languageEnglish
Title of host publication2005 IEEE International Conference on Vehicular Electronics and Safety Proceedings
Pages149-154
Number of pages6
Volume2005
DOIs
Publication statusPublished - 2005
Event2005 IEEE International Conference on Vehicular Electronics and Safety - Xi'an, Shaan'xi
Duration: 2005 Oct 142005 Oct 16

Other

Other2005 IEEE International Conference on Vehicular Electronics and Safety
CityXi'an, Shaan'xi
Period05/10/1405/10/16

Fingerprint

Pattern matching
Computational complexity
Scanning
Object detection

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Li, T., Kamata, S., & Tsuneyoshi, K. (2005). Matching vehicles using hubert scanning distance. In 2005 IEEE International Conference on Vehicular Electronics and Safety Proceedings (Vol. 2005, pp. 149-154). [1563632] https://doi.org/10.1109/ICVES.2005.1563632

Matching vehicles using hubert scanning distance. / Li, Tian; Kamata, Seiichiro; Tsuneyoshi, Kazuyuki.

2005 IEEE International Conference on Vehicular Electronics and Safety Proceedings. Vol. 2005 2005. p. 149-154 1563632.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Li, T, Kamata, S & Tsuneyoshi, K 2005, Matching vehicles using hubert scanning distance. in 2005 IEEE International Conference on Vehicular Electronics and Safety Proceedings. vol. 2005, 1563632, pp. 149-154, 2005 IEEE International Conference on Vehicular Electronics and Safety, Xi'an, Shaan'xi, 05/10/14. https://doi.org/10.1109/ICVES.2005.1563632
Li T, Kamata S, Tsuneyoshi K. Matching vehicles using hubert scanning distance. In 2005 IEEE International Conference on Vehicular Electronics and Safety Proceedings. Vol. 2005. 2005. p. 149-154. 1563632 https://doi.org/10.1109/ICVES.2005.1563632
Li, Tian ; Kamata, Seiichiro ; Tsuneyoshi, Kazuyuki. / Matching vehicles using hubert scanning distance. 2005 IEEE International Conference on Vehicular Electronics and Safety Proceedings. Vol. 2005 2005. pp. 149-154
@inproceedings{b2dceb9ace044be7b8db2c00f5e8b079,
title = "Matching vehicles using hubert scanning distance",
abstract = "Matching objects is a fundamental problem for any object detection system. Feature-based methods in matching objects such as vehicles often encounter the problem of correspondences between features of two related patterns. The features may be points, lines, curves and regions. Point pattern matching (PPM) is a primary and essential approach for establishing a correspondence within two related patterns. Although some well-known Hausdorff distance measures work well for this task, they are very computational expensive and suffer from the noise of images. In this paper, we propose a novel similarity measure using Hilbert curve named Hilbert scanning distance (HSD) to resolve the problems. This method computes the distance measure in one-dimensional (1-D) sequence in stead of in two-dimensional (2-D) image space, which greatly reduce the computational complexity. By applying a threshold elimination function, extreme distances caused by noise and position errors (e.g. those that occur with feature or edge extraction) are removed. The experimental results show that HSD can provide sufficient information for matching -vehicles within low computational complexity. We believe this point out a new direction for the research of PPM.",
author = "Tian Li and Seiichiro Kamata and Kazuyuki Tsuneyoshi",
year = "2005",
doi = "10.1109/ICVES.2005.1563632",
language = "English",
isbn = "0780394356",
volume = "2005",
pages = "149--154",
booktitle = "2005 IEEE International Conference on Vehicular Electronics and Safety Proceedings",

}

TY - GEN

T1 - Matching vehicles using hubert scanning distance

AU - Li, Tian

AU - Kamata, Seiichiro

AU - Tsuneyoshi, Kazuyuki

PY - 2005

Y1 - 2005

N2 - Matching objects is a fundamental problem for any object detection system. Feature-based methods in matching objects such as vehicles often encounter the problem of correspondences between features of two related patterns. The features may be points, lines, curves and regions. Point pattern matching (PPM) is a primary and essential approach for establishing a correspondence within two related patterns. Although some well-known Hausdorff distance measures work well for this task, they are very computational expensive and suffer from the noise of images. In this paper, we propose a novel similarity measure using Hilbert curve named Hilbert scanning distance (HSD) to resolve the problems. This method computes the distance measure in one-dimensional (1-D) sequence in stead of in two-dimensional (2-D) image space, which greatly reduce the computational complexity. By applying a threshold elimination function, extreme distances caused by noise and position errors (e.g. those that occur with feature or edge extraction) are removed. The experimental results show that HSD can provide sufficient information for matching -vehicles within low computational complexity. We believe this point out a new direction for the research of PPM.

AB - Matching objects is a fundamental problem for any object detection system. Feature-based methods in matching objects such as vehicles often encounter the problem of correspondences between features of two related patterns. The features may be points, lines, curves and regions. Point pattern matching (PPM) is a primary and essential approach for establishing a correspondence within two related patterns. Although some well-known Hausdorff distance measures work well for this task, they are very computational expensive and suffer from the noise of images. In this paper, we propose a novel similarity measure using Hilbert curve named Hilbert scanning distance (HSD) to resolve the problems. This method computes the distance measure in one-dimensional (1-D) sequence in stead of in two-dimensional (2-D) image space, which greatly reduce the computational complexity. By applying a threshold elimination function, extreme distances caused by noise and position errors (e.g. those that occur with feature or edge extraction) are removed. The experimental results show that HSD can provide sufficient information for matching -vehicles within low computational complexity. We believe this point out a new direction for the research of PPM.

UR - http://www.scopus.com/inward/record.url?scp=33845967471&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33845967471&partnerID=8YFLogxK

U2 - 10.1109/ICVES.2005.1563632

DO - 10.1109/ICVES.2005.1563632

M3 - Conference contribution

SN - 0780394356

SN - 9780780394353

VL - 2005

SP - 149

EP - 154

BT - 2005 IEEE International Conference on Vehicular Electronics and Safety Proceedings

ER -