BV-Person: A Large-scale dataset for bird-view person re-identification
Person Re-IDentification (ReID) aims at re-identifying persons from non-overlapping cameras. Existing person ReID studies focus on horizontal-view ReID tasks, in which the person images are captured by the cameras from a (nearly) horizontal view. In this work we introduce a new ReID task, bird-view...
Saved in:
Main Authors: | , , , , , , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2021
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/7312 https://ink.library.smu.edu.sg/context/sis_research/article/8315/viewcontent/BV_Person_ICCV_2021_av_oa.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
id |
sg-smu-ink.sis_research-8315 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-83152022-09-29T06:03:21Z BV-Person: A Large-scale dataset for bird-view person re-identification YAN, Cheng PANG, Guansong WANG, Lei JIAO, Jile FENG, Xuetao SHEN, Chunhua LI, Jingjing Person Re-IDentification (ReID) aims at re-identifying persons from non-overlapping cameras. Existing person ReID studies focus on horizontal-view ReID tasks, in which the person images are captured by the cameras from a (nearly) horizontal view. In this work we introduce a new ReID task, bird-view person ReID, which aims at searching for a person in a gallery of horizontal-view images with the query images taken from a bird's-eye view, i.e., an elevated view of an object from above. The task is important because there are a large number of video surveillance cameras capturing persons from such an elevated view at public places. However, it is a challenging task in that the images from the bird view (i) provide limited person appearance information and (ii) have a large discrepancy compared to the persons in the horizontal view. We aim to facilitate the development of person ReID from this line by introducing a large-scale real-world dataset for this task. The proposed dataset, named BV-Person, contains 114k images of 18k identities in which nearly 20k images of 7.4k identities are taken from the bird's-eye view. We further introduce a novel model for this new ReID task. Large-scale experiments are performed to evaluate our model and 11 current state-of-the-art ReID models on BV-Person to establish performance benchmarks from multiple perspectives. The empirical results show that our model consistently and substantially outperforms the state-of-the-art models on all five datasets derived from BV-Person. Our model also achieves state-of-the-art performance on two general ReID datasets. The BV-Person dataset is available at: https://git.io/BVPerson 2021-10-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/7312 info:doi/10.1109/ICCV48922.2021.01076 https://ink.library.smu.edu.sg/context/sis_research/article/8315/viewcontent/BV_Person_ICCV_2021_av_oa.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Datasets and evaluation Image and video retrieval Databases and Information Systems Numerical Analysis and Scientific Computing |
institution |
Singapore Management University |
building |
SMU Libraries |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
SMU Libraries |
collection |
InK@SMU |
language |
English |
topic |
Datasets and evaluation Image and video retrieval Databases and Information Systems Numerical Analysis and Scientific Computing |
spellingShingle |
Datasets and evaluation Image and video retrieval Databases and Information Systems Numerical Analysis and Scientific Computing YAN, Cheng PANG, Guansong WANG, Lei JIAO, Jile FENG, Xuetao SHEN, Chunhua LI, Jingjing BV-Person: A Large-scale dataset for bird-view person re-identification |
description |
Person Re-IDentification (ReID) aims at re-identifying persons from non-overlapping cameras. Existing person ReID studies focus on horizontal-view ReID tasks, in which the person images are captured by the cameras from a (nearly) horizontal view. In this work we introduce a new ReID task, bird-view person ReID, which aims at searching for a person in a gallery of horizontal-view images with the query images taken from a bird's-eye view, i.e., an elevated view of an object from above. The task is important because there are a large number of video surveillance cameras capturing persons from such an elevated view at public places. However, it is a challenging task in that the images from the bird view (i) provide limited person appearance information and (ii) have a large discrepancy compared to the persons in the horizontal view. We aim to facilitate the development of person ReID from this line by introducing a large-scale real-world dataset for this task. The proposed dataset, named BV-Person, contains 114k images of 18k identities in which nearly 20k images of 7.4k identities are taken from the bird's-eye view. We further introduce a novel model for this new ReID task. Large-scale experiments are performed to evaluate our model and 11 current state-of-the-art ReID models on BV-Person to establish performance benchmarks from multiple perspectives. The empirical results show that our model consistently and substantially outperforms the state-of-the-art models on all five datasets derived from BV-Person. Our model also achieves state-of-the-art performance on two general ReID datasets. The BV-Person dataset is available at: https://git.io/BVPerson |
format |
text |
author |
YAN, Cheng PANG, Guansong WANG, Lei JIAO, Jile FENG, Xuetao SHEN, Chunhua LI, Jingjing |
author_facet |
YAN, Cheng PANG, Guansong WANG, Lei JIAO, Jile FENG, Xuetao SHEN, Chunhua LI, Jingjing |
author_sort |
YAN, Cheng |
title |
BV-Person: A Large-scale dataset for bird-view person re-identification |
title_short |
BV-Person: A Large-scale dataset for bird-view person re-identification |
title_full |
BV-Person: A Large-scale dataset for bird-view person re-identification |
title_fullStr |
BV-Person: A Large-scale dataset for bird-view person re-identification |
title_full_unstemmed |
BV-Person: A Large-scale dataset for bird-view person re-identification |
title_sort |
bv-person: a large-scale dataset for bird-view person re-identification |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2021 |
url |
https://ink.library.smu.edu.sg/sis_research/7312 https://ink.library.smu.edu.sg/context/sis_research/article/8315/viewcontent/BV_Person_ICCV_2021_av_oa.pdf |
_version_ |
1770576299059838976 |