Rear obstacle detection system with fisheye stereo camera using HCT

Deukhyeon Kim, Jinwook Choi, Hunjae Yoo, Ukil Yang, Kwanghoon Sohn

Research output: Contribution to journalArticle

13 Citations (Scopus)

Abstract

A vision based rear obstacle detection system is one of the most essential technologies, which can be used in many applications such as a parking assistance systems and intelligent vehicles. Stereo matching based obstacle detection methods have two inherent limitations, including sensitivity to illumination variation and high computational complexity. To overcome these problems, we present a hierarchical census transform (HCT)-based stereo matching method, and proposes a real-time rear obstacle detection system using fisheye stereo cameras. It includes two major components: firstly, we use a hierarchical approach to improve computational efficiency and reduce dependency on a matching window size. Computation time can also be accelerated with compute unified device architecture (CUDA) implementation because we designed the proposed method for parallel processing. Secondly, our method provides more accurate depth information, especially for moving objects, through cost aggregation using color and motion information. Experimental results show satisfactory performance under various real parking environments. The performance of the proposed method is superior to those of the conventional methods in terms of runtime and accuracy of depth estimation. Moreover, correct detection rate of the proposed system is 12.51% better than those of other systems, while its false and miss detection rates are 11.09% and 12.51% lower than those of other detection systems.

Original languageEnglish
Pages (from-to)6295-6305
Number of pages11
JournalExpert Systems with Applications
Volume42
Issue number17-18
DOIs
Publication statusPublished - 2015 May 16

Fingerprint

Parking
Cameras
Intelligent vehicle highway systems
Computational efficiency
Computational complexity
Agglomeration
Lighting
Color
Processing
Costs

All Science Journal Classification (ASJC) codes

  • Engineering(all)
  • Computer Science Applications
  • Artificial Intelligence

Cite this

Kim, Deukhyeon ; Choi, Jinwook ; Yoo, Hunjae ; Yang, Ukil ; Sohn, Kwanghoon. / Rear obstacle detection system with fisheye stereo camera using HCT. In: Expert Systems with Applications. 2015 ; Vol. 42, No. 17-18. pp. 6295-6305.
@article{e3edc01ac5d94b5ebab73096392ff27b,
title = "Rear obstacle detection system with fisheye stereo camera using HCT",
abstract = "A vision based rear obstacle detection system is one of the most essential technologies, which can be used in many applications such as a parking assistance systems and intelligent vehicles. Stereo matching based obstacle detection methods have two inherent limitations, including sensitivity to illumination variation and high computational complexity. To overcome these problems, we present a hierarchical census transform (HCT)-based stereo matching method, and proposes a real-time rear obstacle detection system using fisheye stereo cameras. It includes two major components: firstly, we use a hierarchical approach to improve computational efficiency and reduce dependency on a matching window size. Computation time can also be accelerated with compute unified device architecture (CUDA) implementation because we designed the proposed method for parallel processing. Secondly, our method provides more accurate depth information, especially for moving objects, through cost aggregation using color and motion information. Experimental results show satisfactory performance under various real parking environments. The performance of the proposed method is superior to those of the conventional methods in terms of runtime and accuracy of depth estimation. Moreover, correct detection rate of the proposed system is 12.51{\%} better than those of other systems, while its false and miss detection rates are 11.09{\%} and 12.51{\%} lower than those of other detection systems.",
author = "Deukhyeon Kim and Jinwook Choi and Hunjae Yoo and Ukil Yang and Kwanghoon Sohn",
year = "2015",
month = "5",
day = "16",
doi = "10.1016/j.eswa.2015.04.035",
language = "English",
volume = "42",
pages = "6295--6305",
journal = "Expert Systems with Applications",
issn = "0957-4174",
publisher = "Elsevier Limited",
number = "17-18",

}

Rear obstacle detection system with fisheye stereo camera using HCT. / Kim, Deukhyeon; Choi, Jinwook; Yoo, Hunjae; Yang, Ukil; Sohn, Kwanghoon.

In: Expert Systems with Applications, Vol. 42, No. 17-18, 16.05.2015, p. 6295-6305.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Rear obstacle detection system with fisheye stereo camera using HCT

AU - Kim, Deukhyeon

AU - Choi, Jinwook

AU - Yoo, Hunjae

AU - Yang, Ukil

AU - Sohn, Kwanghoon

PY - 2015/5/16

Y1 - 2015/5/16

N2 - A vision based rear obstacle detection system is one of the most essential technologies, which can be used in many applications such as a parking assistance systems and intelligent vehicles. Stereo matching based obstacle detection methods have two inherent limitations, including sensitivity to illumination variation and high computational complexity. To overcome these problems, we present a hierarchical census transform (HCT)-based stereo matching method, and proposes a real-time rear obstacle detection system using fisheye stereo cameras. It includes two major components: firstly, we use a hierarchical approach to improve computational efficiency and reduce dependency on a matching window size. Computation time can also be accelerated with compute unified device architecture (CUDA) implementation because we designed the proposed method for parallel processing. Secondly, our method provides more accurate depth information, especially for moving objects, through cost aggregation using color and motion information. Experimental results show satisfactory performance under various real parking environments. The performance of the proposed method is superior to those of the conventional methods in terms of runtime and accuracy of depth estimation. Moreover, correct detection rate of the proposed system is 12.51% better than those of other systems, while its false and miss detection rates are 11.09% and 12.51% lower than those of other detection systems.

AB - A vision based rear obstacle detection system is one of the most essential technologies, which can be used in many applications such as a parking assistance systems and intelligent vehicles. Stereo matching based obstacle detection methods have two inherent limitations, including sensitivity to illumination variation and high computational complexity. To overcome these problems, we present a hierarchical census transform (HCT)-based stereo matching method, and proposes a real-time rear obstacle detection system using fisheye stereo cameras. It includes two major components: firstly, we use a hierarchical approach to improve computational efficiency and reduce dependency on a matching window size. Computation time can also be accelerated with compute unified device architecture (CUDA) implementation because we designed the proposed method for parallel processing. Secondly, our method provides more accurate depth information, especially for moving objects, through cost aggregation using color and motion information. Experimental results show satisfactory performance under various real parking environments. The performance of the proposed method is superior to those of the conventional methods in terms of runtime and accuracy of depth estimation. Moreover, correct detection rate of the proposed system is 12.51% better than those of other systems, while its false and miss detection rates are 11.09% and 12.51% lower than those of other detection systems.

UR - http://www.scopus.com/inward/record.url?scp=84929521448&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84929521448&partnerID=8YFLogxK

U2 - 10.1016/j.eswa.2015.04.035

DO - 10.1016/j.eswa.2015.04.035

M3 - Article

VL - 42

SP - 6295

EP - 6305

JO - Expert Systems with Applications

JF - Expert Systems with Applications

SN - 0957-4174

IS - 17-18

ER -