An Effective Pipeline for Pedestrian Detection in Mid-High Density Crowd

Yu Hao, Duke Gledhill, Ying Liu, Jiulun Fan, Zhijie Xu

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

Abstract

A novel framework is introduced to handle the pedestrian detection in mid-high crowd density. This framework exploits the samples obtained with the unsupervised approach, extracts the combined pattern of Histograms of Oriented Gradients (HOG) and Local Binary Pattern (LBP) for the training and detection. The motion information is utilized to adjust the confidence score of detect annotation, and the soft-NMS is used to handle the balance between the removing of redundant annotation and occlusion. The experiments indicate the proposed approach achieved a promising result compared to state-of-the-art trained with the benchmarking dataset.
Original languageEnglish
Title of host publication25th International Conference on Automation & Computing (ICAC 2019)
Subtitle of host publicationImproving Productivity through Automation and Computing
EditorsHui Yu
PublisherIEEE
Pages153-158
Number of pages6
ISBN (Electronic)9781861376657
ISBN (Print)9781728125183
DOIs
Publication statusPublished - 11 Nov 2019
Event25th IEEE International Conference on Automation and Computing: Improving Productivity through Automation and Computing - Lancaster University, Lancaster, United Kingdom
Duration: 5 Sep 20197 Sep 2019
Conference number: 25
http://www.research.lancs.ac.uk/portal/en/activities/25th-ieee-international-conference-on-automation-and-computing-icac19-57-september-2019-lancaster-university-uk(679d94ff-4efb-46b5-9c80-c6d34a13bae4).html

Conference

Conference25th IEEE International Conference on Automation and Computing
Abbreviated titleICAC 2019
CountryUnited Kingdom
CityLancaster
Period5/09/197/09/19
Internet address

Fingerprint

Benchmarking
Pipelines
Experiments

Cite this

Hao, Y., Gledhill, D., Liu, Y., Fan, J., & Xu, Z. (2019). An Effective Pipeline for Pedestrian Detection in Mid-High Density Crowd. In H. Yu (Ed.), 25th International Conference on Automation & Computing (ICAC 2019): Improving Productivity through Automation and Computing (pp. 153-158). IEEE. https://doi.org/10.23919/IConAC.2019.8894985
Hao, Yu ; Gledhill, Duke ; Liu, Ying ; Fan, Jiulun ; Xu, Zhijie. / An Effective Pipeline for Pedestrian Detection in Mid-High Density Crowd. 25th International Conference on Automation & Computing (ICAC 2019): Improving Productivity through Automation and Computing. editor / Hui Yu. IEEE, 2019. pp. 153-158
@inproceedings{c70b7785a4384235a5e876195c3ba4e7,
title = "An Effective Pipeline for Pedestrian Detection in Mid-High Density Crowd",
abstract = "A novel framework is introduced to handle the pedestrian detection in mid-high crowd density. This framework exploits the samples obtained with the unsupervised approach, extracts the combined pattern of Histograms of Oriented Gradients (HOG) and Local Binary Pattern (LBP) for the training and detection. The motion information is utilized to adjust the confidence score of detect annotation, and the soft-NMS is used to handle the balance between the removing of redundant annotation and occlusion. The experiments indicate the proposed approach achieved a promising result compared to state-of-the-art trained with the benchmarking dataset.",
keywords = "Pedestrian detection, HOG, LBP, Soft-NMS, Mid-high crowd density",
author = "Yu Hao and Duke Gledhill and Ying Liu and Jiulun Fan and Zhijie Xu",
year = "2019",
month = "11",
day = "11",
doi = "10.23919/IConAC.2019.8894985",
language = "English",
isbn = "9781728125183",
pages = "153--158",
editor = "Hui Yu",
booktitle = "25th International Conference on Automation & Computing (ICAC 2019)",
publisher = "IEEE",

}

Hao, Y, Gledhill, D, Liu, Y, Fan, J & Xu, Z 2019, An Effective Pipeline for Pedestrian Detection in Mid-High Density Crowd. in H Yu (ed.), 25th International Conference on Automation & Computing (ICAC 2019): Improving Productivity through Automation and Computing. IEEE, pp. 153-158, 25th IEEE International Conference on Automation and Computing, Lancaster, United Kingdom, 5/09/19. https://doi.org/10.23919/IConAC.2019.8894985

An Effective Pipeline for Pedestrian Detection in Mid-High Density Crowd. / Hao, Yu; Gledhill, Duke; Liu, Ying; Fan, Jiulun; Xu, Zhijie.

25th International Conference on Automation & Computing (ICAC 2019): Improving Productivity through Automation and Computing. ed. / Hui Yu. IEEE, 2019. p. 153-158.

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

TY - GEN

T1 - An Effective Pipeline for Pedestrian Detection in Mid-High Density Crowd

AU - Hao, Yu

AU - Gledhill, Duke

AU - Liu, Ying

AU - Fan, Jiulun

AU - Xu, Zhijie

PY - 2019/11/11

Y1 - 2019/11/11

N2 - A novel framework is introduced to handle the pedestrian detection in mid-high crowd density. This framework exploits the samples obtained with the unsupervised approach, extracts the combined pattern of Histograms of Oriented Gradients (HOG) and Local Binary Pattern (LBP) for the training and detection. The motion information is utilized to adjust the confidence score of detect annotation, and the soft-NMS is used to handle the balance between the removing of redundant annotation and occlusion. The experiments indicate the proposed approach achieved a promising result compared to state-of-the-art trained with the benchmarking dataset.

AB - A novel framework is introduced to handle the pedestrian detection in mid-high crowd density. This framework exploits the samples obtained with the unsupervised approach, extracts the combined pattern of Histograms of Oriented Gradients (HOG) and Local Binary Pattern (LBP) for the training and detection. The motion information is utilized to adjust the confidence score of detect annotation, and the soft-NMS is used to handle the balance between the removing of redundant annotation and occlusion. The experiments indicate the proposed approach achieved a promising result compared to state-of-the-art trained with the benchmarking dataset.

KW - Pedestrian detection

KW - HOG

KW - LBP

KW - Soft-NMS

KW - Mid-high crowd density

UR - https://www.scopus.com/record/display.uri?eid=2-s2.0-85075783363&origin=resultslist&sort=plf-f&src=s&st1=An+Effective+Pipeline+for+Pedestrian+Detection+in+Mid-High+Density+Crowd+&st2=&sid=b6cad3a9680b32d9f8ee3dbc1e9257c0&sot=b&sdt=b&sl=88&s=TITLE-ABS-KEY%28An+Effective+Pipeline+for+Pedestrian+Detection+in+Mid-High+Density+Crowd+%29&relpos=0&citeCnt=0&searchTerm=

U2 - 10.23919/IConAC.2019.8894985

DO - 10.23919/IConAC.2019.8894985

M3 - Conference contribution

SN - 9781728125183

SP - 153

EP - 158

BT - 25th International Conference on Automation & Computing (ICAC 2019)

A2 - Yu, Hui

PB - IEEE

ER -

Hao Y, Gledhill D, Liu Y, Fan J, Xu Z. An Effective Pipeline for Pedestrian Detection in Mid-High Density Crowd. In Yu H, editor, 25th International Conference on Automation & Computing (ICAC 2019): Improving Productivity through Automation and Computing. IEEE. 2019. p. 153-158 https://doi.org/10.23919/IConAC.2019.8894985