NUS/BUAA-PRO is the abbreviation
for 'NUS/BUAA People and Rigid Objects Dataset', which contains
365 image sequences with manually labeled bounding boxes and
occlusion status. 150 sequences are further annotated with
pixel-level masks.
NUS-PRO
Data: Baidu, Google Drive (part 1, part 2), Mega
View tool: Baidu, Google Drive, Mega
Code used in the reference paper: Baidu, Google Drive, Mega
BUAA-PRO
Code & data package: Baidu (access code: b9qi), Dropbox
(Original image data can be found in NUS-PRO)
@article{nus_pro,
title={{NUS-PRO: A New Visual Tracking Challenge}},
author={Li, A and Lin, M and Wu, Y and Yang, MH and Yan, S},
journal={ IEEE Transactions on Pattern Analysis and Machine Intelligence},
volume={38},
number={2},
pages={335--349},
year={2016}
}
@inproceedings{buaa_pro,
title={{BUAA-PRO: A Tracking Dataset with Pixel-Level Annotation}},
author={Li, Annan and Chen, Zhiyuan and Wang, Yunhong},
booktitle={British Machine Vision Conference},
year={2018}
}
