A novel set of pixel difference-based features for pedestrian detection

Xing Liu; Kar Ann Toh

doi:10.1109/ISBA.2018.8311456

A novel set of pixel difference-based features for pedestrian detection

Xing Liu, Kar Ann Toh

Department of Electrical and Electronic Engineering

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

2 Citations (Scopus)

Abstract

We propose a feature extraction pipeline namely Difference Matrix Projection (DMP)for pedestrian detection. The goal is to design an effective feature set that can be efficiently computed. Our feature consists of pixel differences at different scales and orientations coupled with average pooling and block normalization. We develop a formulation that computes the difference maps and local average using global image projection instead of an iterative filtering. As a result, the computations can be expressed by analytic equations in terms of the input image. The projection matrices are pre-constructed, so they are readily applied to the image for feature extraction. Experiment results on the Daimler Chrysler (Daimler-CB) and NICTA pedestrian datasets show encouraging results, especially for low-resolution samples.

Original language	English
Title of host publication	2018 IEEE 4th International Conference on Identity, Security, and Behavior Analysis, ISBA 2018
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1-6
Number of pages	6
ISBN (Electronic)	9781538622483
DOIs	https://doi.org/10.1109/ISBA.2018.8311456
Publication status	Published - 2018 Mar 9
Event	4th IEEE International Conference on Identity, Security, and Behavior Analysis, ISBA 2018 - Singapore, Singapore Duration: 2018 Jan 11 → 2018 Jan 12

Publication series

Name	2018 IEEE 4th International Conference on Identity, Security, and Behavior Analysis, ISBA 2018
Volume	2018-January

Other

Other	4th IEEE International Conference on Identity, Security, and Behavior Analysis, ISBA 2018
Country/Territory	Singapore
City	Singapore
Period	18/1/11 → 18/1/12

Bibliographical note

Publisher Copyright:
© 2018 IEEE.

All Science Journal Classification (ASJC) codes

Computer Networks and Communications
Computer Vision and Pattern Recognition
Safety, Risk, Reliability and Quality
Behavioral Neuroscience
Social Sciences (miscellaneous)

Access to Document

10.1109/ISBA.2018.8311456

Cite this

Liu, X., & Toh, K. A. (2018). A novel set of pixel difference-based features for pedestrian detection. In 2018 IEEE 4th International Conference on Identity, Security, and Behavior Analysis, ISBA 2018 (pp. 1-6). (2018 IEEE 4th International Conference on Identity, Security, and Behavior Analysis, ISBA 2018; Vol. 2018-January). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISBA.2018.8311456

@inproceedings{4b972a67fc104768af818e4738969869,

title = "A novel set of pixel difference-based features for pedestrian detection",

abstract = "We propose a feature extraction pipeline namely Difference Matrix Projection (DMP)for pedestrian detection. The goal is to design an effective feature set that can be efficiently computed. Our feature consists of pixel differences at different scales and orientations coupled with average pooling and block normalization. We develop a formulation that computes the difference maps and local average using global image projection instead of an iterative filtering. As a result, the computations can be expressed by analytic equations in terms of the input image. The projection matrices are pre-constructed, so they are readily applied to the image for feature extraction. Experiment results on the Daimler Chrysler (Daimler-CB) and NICTA pedestrian datasets show encouraging results, especially for low-resolution samples.",

author = "Xing Liu and Toh, {Kar Ann}",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 4th IEEE International Conference on Identity, Security, and Behavior Analysis, ISBA 2018 ; Conference date: 11-01-2018 Through 12-01-2018",

year = "2018",

month = mar,

day = "9",

doi = "10.1109/ISBA.2018.8311456",

language = "English",

series = "2018 IEEE 4th International Conference on Identity, Security, and Behavior Analysis, ISBA 2018",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1--6",

booktitle = "2018 IEEE 4th International Conference on Identity, Security, and Behavior Analysis, ISBA 2018",

address = "United States",

}

Liu, X & Toh, KA 2018, A novel set of pixel difference-based features for pedestrian detection. in 2018 IEEE 4th International Conference on Identity, Security, and Behavior Analysis, ISBA 2018. 2018 IEEE 4th International Conference on Identity, Security, and Behavior Analysis, ISBA 2018, vol. 2018-January, Institute of Electrical and Electronics Engineers Inc., pp. 1-6, 4th IEEE International Conference on Identity, Security, and Behavior Analysis, ISBA 2018, Singapore, Singapore, 18/1/11. https://doi.org/10.1109/ISBA.2018.8311456

A novel set of pixel difference-based features for pedestrian detection. / Liu, Xing; Toh, Kar Ann.
2018 IEEE 4th International Conference on Identity, Security, and Behavior Analysis, ISBA 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 1-6 (2018 IEEE 4th International Conference on Identity, Security, and Behavior Analysis, ISBA 2018; Vol. 2018-January).

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

TY - GEN

T1 - A novel set of pixel difference-based features for pedestrian detection

AU - Liu, Xing

AU - Toh, Kar Ann

PY - 2018/3/9

Y1 - 2018/3/9

N2 - We propose a feature extraction pipeline namely Difference Matrix Projection (DMP)for pedestrian detection. The goal is to design an effective feature set that can be efficiently computed. Our feature consists of pixel differences at different scales and orientations coupled with average pooling and block normalization. We develop a formulation that computes the difference maps and local average using global image projection instead of an iterative filtering. As a result, the computations can be expressed by analytic equations in terms of the input image. The projection matrices are pre-constructed, so they are readily applied to the image for feature extraction. Experiment results on the Daimler Chrysler (Daimler-CB) and NICTA pedestrian datasets show encouraging results, especially for low-resolution samples.

AB - We propose a feature extraction pipeline namely Difference Matrix Projection (DMP)for pedestrian detection. The goal is to design an effective feature set that can be efficiently computed. Our feature consists of pixel differences at different scales and orientations coupled with average pooling and block normalization. We develop a formulation that computes the difference maps and local average using global image projection instead of an iterative filtering. As a result, the computations can be expressed by analytic equations in terms of the input image. The projection matrices are pre-constructed, so they are readily applied to the image for feature extraction. Experiment results on the Daimler Chrysler (Daimler-CB) and NICTA pedestrian datasets show encouraging results, especially for low-resolution samples.

UR - http://www.scopus.com/inward/record.url?scp=85049809150&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85049809150&partnerID=8YFLogxK

U2 - 10.1109/ISBA.2018.8311456

DO - 10.1109/ISBA.2018.8311456

M3 - Conference contribution

AN - SCOPUS:85049809150

T3 - 2018 IEEE 4th International Conference on Identity, Security, and Behavior Analysis, ISBA 2018

SP - 1

EP - 6

BT - 2018 IEEE 4th International Conference on Identity, Security, and Behavior Analysis, ISBA 2018

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 4th IEEE International Conference on Identity, Security, and Behavior Analysis, ISBA 2018

Y2 - 11 January 2018 through 12 January 2018

ER -

Liu X, Toh KA. A novel set of pixel difference-based features for pedestrian detection. In 2018 IEEE 4th International Conference on Identity, Security, and Behavior Analysis, ISBA 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 1-6. (2018 IEEE 4th International Conference on Identity, Security, and Behavior Analysis, ISBA 2018). doi: 10.1109/ISBA.2018.8311456

A novel set of pixel difference-based features for pedestrian detection

Abstract

Publication series

Other

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this