Robustness analysis of pedestrian detectors for surveillance

To obtain effective pedestrian detection results in surveillance video, there have been many methods proposed to handle the problems from severe occlusion, pose variation, clutter background, and so on. Besides detection accuracy, a robust surveillance video system should be stable to video quality...

Full description

Saved in:
Bibliographic Details
Main Authors: Fang, Yuming, Ding, Guanqun, Yuan, Yuan, Lin, Weisi, Liu, Haiwen
Other Authors: School of Computer Science and Engineering
Format: Article
Language:English
Published: 2018
Subjects:
Online Access:https://hdl.handle.net/10356/87575
http://hdl.handle.net/10220/45447
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-87575
record_format dspace
spelling sg-ntu-dr.10356-875752020-03-07T11:48:58Z Robustness analysis of pedestrian detectors for surveillance Fang, Yuming Ding, Guanqun Yuan, Yuan Lin, Weisi Liu, Haiwen School of Computer Science and Engineering Object Detection Video Surveillance To obtain effective pedestrian detection results in surveillance video, there have been many methods proposed to handle the problems from severe occlusion, pose variation, clutter background, and so on. Besides detection accuracy, a robust surveillance video system should be stable to video quality degradation by network transmission, environment variation, and so on. In this paper, we conduct the research on the robustness of pedestrian detection algorithms to video quality degradation. The main contribution of this paper includes the following three aspects. First, a large-scale distorted surveillance video data set (DSurVD) is constructed from high-quality video sequences and their corresponding distorted versions. Second, we design a method to evaluate detection stability and a robustness measure called robustness quadrangle, which can be adopted to the visualize detection accuracy of pedestrian detection algorithms on high-quality video sequences and stability with video quality degradation. Third, the robustness of seven existing pedestrian detection algorithms is evaluated by the built DSurVD. Experimental results show that the robustness can be further improved for existing pedestrian detection algorithms. In addition, we provide much in-depth discussion on how different distortion types influence the performance of pedestrian detection algorithms, which is important to design effective pedestrian detection algorithms for surveillance. Published version 2018-08-03T06:26:48Z 2019-12-06T16:44:48Z 2018-08-03T06:26:48Z 2019-12-06T16:44:48Z 2018 Journal Article Fang, Y., Ding, G., Yuan, Y., Lin, W., & Liu, H. (2018). Robustness analysis of pedestrian detectors for surveillance. IEEE Access, 6, 28890-28902. https://hdl.handle.net/10356/87575 http://hdl.handle.net/10220/45447 10.1109/ACCESS.2018.2840329 en IEEE Access © 2018 IEEE. Translations and content mining are permitted for academic research only. Personal use is also permitted, but republication/redistribution requires IEEE permission. See http://www.ieee.org/publications_standards/publications/rights/index.html for more information 13 p. application/pdf
institution Nanyang Technological University
building NTU Library
country Singapore
collection DR-NTU
language English
topic Object Detection
Video Surveillance
spellingShingle Object Detection
Video Surveillance
Fang, Yuming
Ding, Guanqun
Yuan, Yuan
Lin, Weisi
Liu, Haiwen
Robustness analysis of pedestrian detectors for surveillance
description To obtain effective pedestrian detection results in surveillance video, there have been many methods proposed to handle the problems from severe occlusion, pose variation, clutter background, and so on. Besides detection accuracy, a robust surveillance video system should be stable to video quality degradation by network transmission, environment variation, and so on. In this paper, we conduct the research on the robustness of pedestrian detection algorithms to video quality degradation. The main contribution of this paper includes the following three aspects. First, a large-scale distorted surveillance video data set (DSurVD) is constructed from high-quality video sequences and their corresponding distorted versions. Second, we design a method to evaluate detection stability and a robustness measure called robustness quadrangle, which can be adopted to the visualize detection accuracy of pedestrian detection algorithms on high-quality video sequences and stability with video quality degradation. Third, the robustness of seven existing pedestrian detection algorithms is evaluated by the built DSurVD. Experimental results show that the robustness can be further improved for existing pedestrian detection algorithms. In addition, we provide much in-depth discussion on how different distortion types influence the performance of pedestrian detection algorithms, which is important to design effective pedestrian detection algorithms for surveillance.
author2 School of Computer Science and Engineering
author_facet School of Computer Science and Engineering
Fang, Yuming
Ding, Guanqun
Yuan, Yuan
Lin, Weisi
Liu, Haiwen
format Article
author Fang, Yuming
Ding, Guanqun
Yuan, Yuan
Lin, Weisi
Liu, Haiwen
author_sort Fang, Yuming
title Robustness analysis of pedestrian detectors for surveillance
title_short Robustness analysis of pedestrian detectors for surveillance
title_full Robustness analysis of pedestrian detectors for surveillance
title_fullStr Robustness analysis of pedestrian detectors for surveillance
title_full_unstemmed Robustness analysis of pedestrian detectors for surveillance
title_sort robustness analysis of pedestrian detectors for surveillance
publishDate 2018
url https://hdl.handle.net/10356/87575
http://hdl.handle.net/10220/45447
_version_ 1681047212679757824