Improving Person Re-identification by Segmentation-Based Detection Bounding Box Filtering
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-identi_cation pipeline discards the automated detections that are of poor quality due to occlusions, misplaced re...
| Published in: | Journal of Universal Computer Science |
|---|---|
| Main Authors: | , , |
| Format: | Article |
| Language: | English |
| Published: |
Graz University of Technology
2019-06-01
|
| Subjects: | |
| Online Access: | https://lib.jucs.org/article/22615/download/pdf/ |
| _version_ | 1852727524431233024 |
|---|---|
| author | Dominik Pieczyński Marek Kraft Michał Fularz |
| author_facet | Dominik Pieczyński Marek Kraft Michał Fularz |
| author_sort | Dominik Pieczyński |
| collection | DOAJ |
| container_title | Journal of Universal Computer Science |
| description | 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-identi_cation pipeline 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. using a simple segment number, bounding box fill rate and aspect ratio check. Assuming that a joint detector-segmented approach is used, the additional cost associated with the use of the proposed approach is very low. |
| format | Article |
| id | doaj-art-bc341827eab148ae8eae368f514b2a7a |
| institution | Directory of Open Access Journals |
| issn | 0948-6968 |
| language | English |
| publishDate | 2019-06-01 |
| publisher | Graz University of Technology |
| record_format | Article |
| spelling | doaj-art-bc341827eab148ae8eae368f514b2a7a2025-08-19T21:09:57ZengGraz University of TechnologyJournal of Universal Computer Science0948-69682019-06-0125661162610.3217/jucs-025-06-061122615Improving Person Re-identification by Segmentation-Based Detection Bounding Box FilteringDominik Pieczyński0Marek Kraft1Michał Fularz2Poznań University of TechnologyPoznań University of TechnologyPoznań University of TechnologyIn 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-identi_cation pipeline 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. using a simple segment number, bounding box fill rate and aspect ratio check. Assuming that a joint detector-segmented approach is used, the additional cost associated with the use of the proposed approach is very low.https://lib.jucs.org/article/22615/download/pdf/person re-identificationcomputer visiondeep le |
| spellingShingle | Dominik Pieczyński Marek Kraft Michał Fularz Improving Person Re-identification by Segmentation-Based Detection Bounding Box Filtering person re-identification computer vision deep le |
| title | Improving Person Re-identification by Segmentation-Based Detection Bounding Box Filtering |
| title_full | Improving Person Re-identification by Segmentation-Based Detection Bounding Box Filtering |
| title_fullStr | Improving Person Re-identification by Segmentation-Based Detection Bounding Box Filtering |
| title_full_unstemmed | Improving Person Re-identification by Segmentation-Based Detection Bounding Box Filtering |
| title_short | Improving Person Re-identification by Segmentation-Based Detection Bounding Box Filtering |
| title_sort | improving person re identification by segmentation based detection bounding box filtering |
| topic | person re-identification computer vision deep le |
| url | https://lib.jucs.org/article/22615/download/pdf/ |
| work_keys_str_mv | AT dominikpieczynski improvingpersonreidentificationbysegmentationbaseddetectionboundingboxfiltering AT marekkraft improvingpersonreidentificationbysegmentationbaseddetectionboundingboxfiltering AT michałfularz improvingpersonreidentificationbysegmentationbaseddetectionboundingboxfiltering |