Pedestrian Detection Using Regression-Based Feature Selection and Disparity Map

Chung Hee Lee

doi:10.1007/978-981-15-9343-7_72

Pedestrian Detection Using Regression-Based Feature Selection and Disparity Map

Chung Hee Lee

Division of Electronics & Information System

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

In this paper, the pedestrian detection using a regression-based feature selection and a disparity map method is proposed for improving the processing speed. Using many features helps to improve detection performance, but slows down processing. Therefore, it is important to select and use features efficiently. Our proposed method consists of three stages, such as a disparity map-based detection stage, a segmentation stage using a transformed disparity map, and a recognition stage with regression-based feature analysis. Through experiments with the ETH database, we show that the proposed method improves detection performance and especially processing speed.

Original language	English
Title of host publication	Advances in Computer Science and Ubiquitous Computing - CSA-CUTE 2019
Editors	James J. Park, Simon James Fong, Yi Pan, Yunsick Sung
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	515-520
Number of pages	6
ISBN (Print)	9789811593420
DOIs	https://doi.org/10.1007/978-981-15-9343-7_72
State	Published - 2021
Event	11th International Conference on Computer Science and its Applications, CSA 2019 and 14th KIPS International Conference on Ubiquitous Information Technologies and Applications, CUTE 2019 - Macao, China Duration: 18 Dec 2019 → 20 Dec 2019

Publication series

Name	Lecture Notes in Electrical Engineering
Volume	715
ISSN (Print)	1876-1100
ISSN (Electronic)	1876-1119

Conference

Conference	11th International Conference on Computer Science and its Applications, CSA 2019 and 14th KIPS International Conference on Ubiquitous Information Technologies and Applications, CUTE 2019
Country/Territory	China
City	Macao
Period	18/12/19 → 20/12/19

Bibliographical note

Publisher Copyright:
© 2021, Springer Nature Singapore Pte Ltd.

Keywords

Detection
Disparity map
Regression

Access to Document

10.1007/978-981-15-9343-7_72

Cite this

Lee, C. H. (2021). Pedestrian Detection Using Regression-Based Feature Selection and Disparity Map. In J. J. Park, S. J. Fong, Y. Pan, & Y. Sung (Eds.), Advances in Computer Science and Ubiquitous Computing - CSA-CUTE 2019 (pp. 515-520). (Lecture Notes in Electrical Engineering; Vol. 715). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-15-9343-7_72

@inproceedings{dec2db4dcef94f9c8ce6aaf11cae748d,

title = "Pedestrian Detection Using Regression-Based Feature Selection and Disparity Map",

abstract = "In this paper, the pedestrian detection using a regression-based feature selection and a disparity map method is proposed for improving the processing speed. Using many features helps to improve detection performance, but slows down processing. Therefore, it is important to select and use features efficiently. Our proposed method consists of three stages, such as a disparity map-based detection stage, a segmentation stage using a transformed disparity map, and a recognition stage with regression-based feature analysis. Through experiments with the ETH database, we show that the proposed method improves detection performance and especially processing speed.",

keywords = "Detection, Disparity map, Regression",

author = "Lee, \{Chung Hee\}",

note = "Publisher Copyright: {\textcopyright} 2021, Springer Nature Singapore Pte Ltd.; 11th International Conference on Computer Science and its Applications, CSA 2019 and 14th KIPS International Conference on Ubiquitous Information Technologies and Applications, CUTE 2019 ; Conference date: 18-12-2019 Through 20-12-2019",

year = "2021",

doi = "10.1007/978-981-15-9343-7\_72",

language = "English",

isbn = "9789811593420",

series = "Lecture Notes in Electrical Engineering",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "515--520",

editor = "Park, \{James J.\} and Fong, \{Simon James\} and Yi Pan and Yunsick Sung",

booktitle = "Advances in Computer Science and Ubiquitous Computing - CSA-CUTE 2019",

}

Lee, CH 2021, Pedestrian Detection Using Regression-Based Feature Selection and Disparity Map. in JJ Park, SJ Fong, Y Pan & Y Sung (eds), Advances in Computer Science and Ubiquitous Computing - CSA-CUTE 2019. Lecture Notes in Electrical Engineering, vol. 715, Springer Science and Business Media Deutschland GmbH, pp. 515-520, 11th International Conference on Computer Science and its Applications, CSA 2019 and 14th KIPS International Conference on Ubiquitous Information Technologies and Applications, CUTE 2019, Macao, China, 18/12/19. https://doi.org/10.1007/978-981-15-9343-7_72

Pedestrian Detection Using Regression-Based Feature Selection and Disparity Map. / Lee, Chung Hee.
Advances in Computer Science and Ubiquitous Computing - CSA-CUTE 2019. ed. / James J. Park; Simon James Fong; Yi Pan; Yunsick Sung. Springer Science and Business Media Deutschland GmbH, 2021. p. 515-520 (Lecture Notes in Electrical Engineering; Vol. 715).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Pedestrian Detection Using Regression-Based Feature Selection and Disparity Map

AU - Lee, Chung Hee

PY - 2021

Y1 - 2021

N2 - In this paper, the pedestrian detection using a regression-based feature selection and a disparity map method is proposed for improving the processing speed. Using many features helps to improve detection performance, but slows down processing. Therefore, it is important to select and use features efficiently. Our proposed method consists of three stages, such as a disparity map-based detection stage, a segmentation stage using a transformed disparity map, and a recognition stage with regression-based feature analysis. Through experiments with the ETH database, we show that the proposed method improves detection performance and especially processing speed.

AB - In this paper, the pedestrian detection using a regression-based feature selection and a disparity map method is proposed for improving the processing speed. Using many features helps to improve detection performance, but slows down processing. Therefore, it is important to select and use features efficiently. Our proposed method consists of three stages, such as a disparity map-based detection stage, a segmentation stage using a transformed disparity map, and a recognition stage with regression-based feature analysis. Through experiments with the ETH database, we show that the proposed method improves detection performance and especially processing speed.

KW - Detection

KW - Disparity map

KW - Regression

UR - https://www.scopus.com/pages/publications/85101550301

U2 - 10.1007/978-981-15-9343-7_72

DO - 10.1007/978-981-15-9343-7_72

M3 - Conference contribution

AN - SCOPUS:85101550301

SN - 9789811593420

T3 - Lecture Notes in Electrical Engineering

SP - 515

EP - 520

BT - Advances in Computer Science and Ubiquitous Computing - CSA-CUTE 2019

A2 - Park, James J.

A2 - Fong, Simon James

A2 - Pan, Yi

A2 - Sung, Yunsick

PB - Springer Science and Business Media Deutschland GmbH

T2 - 11th International Conference on Computer Science and its Applications, CSA 2019 and 14th KIPS International Conference on Ubiquitous Information Technologies and Applications, CUTE 2019

Y2 - 18 December 2019 through 20 December 2019

ER -

Pedestrian Detection Using Regression-Based Feature Selection and Disparity Map

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this