Using Segmentation Priors to Improve the Video Surveillance Person Re-Identification Accuracy

Dominik Pieczyński; Marek Kraft; Michał Fularz

doi:10.1007/978-3-030-03658-4_16

Scientific Information System of the Poznań University of Technology

PL EN

Main page / Publications / Using Segmentation Priors to Improve the Video Surveillance Person Re-Identification Accuracy

Submit a comment

Chapter

Download BibTeX

Title

Using Segmentation Priors to Improve the Video Surveillance Person Re-Identification Accuracy

Authors

Dominik Pieczyński (WE) ^{[ 1 ][ 2.2 ][ P ]}
Marek Kraft (WE) ^{[ 1 ][ 2.2 ][ P ]}
Michał Fularz (WE) ^{[ 1 ][ 2.2 ][ P ]}

^{[ 1 ]} Instytut Automatyki, Robotyki i Inżynierii Informatycznej, Wydział Elektryczny, Politechnika Poznańska | ^{[ P ]} employee

Scientific discipline (Law 2.0)

[2.2] Automation, electronics and electrical engineering

Year of publication

2019

Chapter type

chapter in monograph / paper

Publication language

english

Abstract

EN In this paper, a method for improving the quality of person re-identification results is presented. The method is based on the assumption, that including segmentation information into re-identification pipeline suppresses the influence of the background and discards the automated detections that are of poor quality due to occlusions, misplaced regions of interest (ROI), multiple persons found within a single ROI etc. Assuming that a joint detector-segmented approach is used, the additional cost associated with the use of the proposed approach is very low.

Date of online publication

01.11.2018

Pages (from - to)

132 - 139

DOI

10.1007/978-3-030-03658-4_16

URL

https://link.springer.com/chapter/10.1007/978-3-030-03658-4_16

Book

Image Processing and Communications Challenges 10 : 10th International Conference, IP&C’2018 Bydgoszcz, Poland, November 2018, Proceedings

Presented on

10th International Conference on Image Processing and Communications, IP&C’2018, 11.2018, Bydgoszcz, Poland